whatmodel.sh · find the best AI models you can run

Best AI models for a 32GB graphics card

A leaderboard of the best AI models for a 32GB graphics card (with 32GB of system RAM). The best one that runs on it right now is Qwen3.8 27B, followed by Ornith 1.5 35B-A3B and KAT-Coder-V2.5-Dev (35B-A3B). Models are ranked by one score that combines 472 published benchmarks. Models that run on it show the download that fits and the command to run it.

671 models · scores combine 472 benchmarks · updated how it works · find a leaderboard · benchmark your machine
task[all tasks][agent tasks][coding][chat & writing][math][vision & documents][web search]
Models for 32GB RAM · 32GB graphics card → ~32GB fast · reset
+ more
card[RTX 5090][RTX 5000 Ada][RTX PRO 4500 Blackwell]

Detect your exact chip or graphics card:

curl -G whatmodel.sh/ -d max=0 --data-urlencode "mac=$(sysctl -n hw.memsize machdep.cpu.brand_string)"Mac

curl -G whatmodel.sh/ -d max=0 --data-urlencode "ram=$(awk '/MemT/{print $2}' /proc/meminfo)" --data-urlencode "nv=$(nvidia-smi --query-gpu=name,memory.total --format=csv,noheader 2>/dev/null)"Linux

curl.exe -G whatmodel.sh/ -d max=0 --data-urlencode "ram=$((gcim Win32_ComputerSystem).TotalPhysicalMemory)" --data-urlencode "nv=$(nvidia-smi --query-gpu=name,memory.total --format=csv,noheader 2>$null)"Windows

$ terminal

detecting your OS…

Run curl "whatmodel.sh/?ram=32&gpu=card&vram=32"to get this list in your terminal (add &format=json for agents).

ram[8][16][24][32][48][64][96][128][192][256]GB
gpu[apple silicon][graphics card][none]
vram[1][2][4][8][12][16][24][32][48][64][80][96][128][160]GB
price[local][$0.02][$0.1][$0.5][$2][$10][$50][any]max per M

detecting your OS…

Score vs API price

#modelscore↓where↓speed↓RAM↓context↓get itsources
#modelscore↓where↓speed↓RAM↓context↓get itsources
1GPT-6 Astra OpenAI87±1api $20.00/M1.1Mplatform.openai.com ↗Epoch AI — internal evaluationsLMArena leaderboard datasetMathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsOpenAI vendor-reported benchmark scores for its own models (openai.com announcement posts and Deployment Safety Hub system cards)KlinikeBench: Evaluating Language Models Beyond Diagnostic Accuracy (arXiv:2609.38480v2)Roblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau Leetcode+4
2Claude Opus 5.5 Anthropic87±1api $8.00/M1Mdocs.anthropic.com ↗Epoch AI — internal evaluationsAnthropic system cards and model announcements (lab-reported scores)LMArena leaderboard datasetTerminal-Bench 4.0 official leaderboard submissionsKlinikeBench: Evaluating Language Models Beyond Diagnostic Accuracy (arXiv:2609.38480v2)Roblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau Leetcode+1
3GPT-6.1 Sol OpenAI85±1api $4.00/M1.1Mdevelopers.openai.com ↗Epoch AI — internal evaluationsLMArena leaderboard datasetTerminal-Bench 4.0 official leaderboard submissionsRoblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau LeetcodeOpenAI vendor-reported benchmark scores for its own models (openai.com announcement posts and Deployment Safety Hub system cards)Miðeind Icelandic LLM Leaderboard
4Claude Fable 5.1 Anthropic85±1api $20.00/M1Mdocs.anthropic.com ↗Epoch AI — internal evaluationsAnthropic system cards and model announcements (lab-reported scores)LMArena leaderboard datasetMathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsTerminal-Bench 4.0 official leaderboard submissionsRoblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau Leetcode+1
5Claude Sonnet 5.5 Anthropic84±1api $4.00/M1Mplatform.claude.com ↗Epoch AI — internal evaluationsAnthropic system cards and model announcements (lab-reported scores)LMArena leaderboard datasetTerminal-Bench 4.0 official leaderboard submissionsRoblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau LeetcodeMiðeind Icelandic LLM Leaderboard
6Claude Opus 5 Anthropic83±1api $10.00/M1Mdocs.anthropic.com ↗Epoch AI — internal evaluationsAnthropic system cards and model announcements (lab-reported scores)LMArena leaderboard datasetMathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsDaekeun Kim Korean LLM benchmark runsTerminal-Bench 4.0 official leaderboard submissions+11
7GPT-6 Sol OpenAI83±1api $4.00/M1.1Mplatform.openai.com ↗Epoch AI — internal evaluationsLMArena leaderboard datasetTerminal-Bench 4.0 official leaderboard submissionsOpenAI vendor-reported benchmark scores for its own models (openai.com announcement posts and Deployment Safety Hub system cards)Roblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau LeetcodeMiðeind Icelandic LLM Leaderboard+1
8GPT-5.5 Pro OpenAI82±1api $67.50/M1.1Mdevelopers.openai.com ↗Epoch AI — internal evaluationsOpenAI vendor-reported benchmark scores for its own models (openai.com announcement posts and Deployment Safety Hub system cards)
9Gemini 4 Argon (limited preview) Google82±1limited previewLMArena leaderboard datasetGoogle DeepMind Gemini model page and model cards (lab-reported scores)
10GPT-5.6 Sol OpenAI82±1api $8.00/M1.1Mplatform.openai.com ↗Epoch AI — internal evaluationsOpenAI vendor-reported benchmark scores for its own models (openai.com announcement posts and Deployment Safety Hub system cards)LMArena leaderboard datasetMathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsDaekeun Kim Korean LLM benchmark runsTerminal-Bench 4.0 official leaderboard submissions+14
11Claude Fable 5 Anthropic81±1api $20.00/M1Mdocs.anthropic.com ↗Epoch AI — internal evaluationsAnthropic system cards and model announcements (lab-reported scores)MathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsLMArena leaderboard datasetTerminal-Bench 4.0 official leaderboard submissionsτ²/τ³-bench leaderboard: Sierra's own evaluation runs+5
12Claude Mythos Preview (limited preview) Anthropic81±1†limited preview1MAnthropic system cards and model announcements (lab-reported scores)
13GPT-5.4 Pro OpenAI81±1api $67.50/M1.1Mdevelopers.openai.com ↗Epoch AI — internal evaluationsOpenAI vendor-reported benchmark scores for its own models (openai.com announcement posts and Deployment Safety Hub system cards)MathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsARC Prize Foundation model_baseline outputs on ARC-AGI-1/2 public evaluation setsVectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
14GPT-5.5 OpenAI80±1api $11.25/M1.1Mplatform.openai.com ↗Epoch AI — internal evaluationsMathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsOpenAI vendor-reported benchmark scores for its own models (openai.com announcement posts and Deployment Safety Hub system cards)LMArena leaderboard datasetmeituan-longcat/LongCat-2.0 model cardAgents' Last Exam — authors' own fixed-harness model comparison+15
15MiMo-V2.6-Pro Xiaomi79±1api $0.54/M~443GB1Mmimo.mi.com ↗LMArena leaderboard datasetXiaomi MiMo official model cards and documentation
16Hy4 preview (770B-A49B) Tencent79±1api $1.25/M~248GB1Mcloud.tencent.com ↗Tencent Hy4 preview model cardLMArena leaderboard dataset
17GPT-5.6 Terra OpenAI79±1api $4.50/M1.1Mplatform.openai.com ↗Epoch AI — internal evaluationsOpenAI vendor-reported benchmark scores for its own models (openai.com announcement posts and Deployment Safety Hub system cards)LMArena leaderboard datasetDaekeun Kim Korean LLM benchmark runsTerminal-Bench 4.0 official leaderboard submissionsE2E-SWE: Benchmarking LLMs on Building Working Codebases from Scratch (arXiv:2609.38335v1)+5
18Qwen3.8 Max (2.4T-A95B) Alibaba78±1api $3.00/M~380GB262kdeepinfra.com ↗Epoch AI — internal evaluationsMathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsLMArena leaderboard datasetQwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)GameLogicBench: Evaluating Coding Agents on Runtime Game Logic with Tick-Level State Assertions (arXiv:2609.21562v2)τ²/τ³-bench leaderboard: Sierra's own evaluation runs+2
19Claude Opus 4.8 Anthropic78±0api $10.00/M1Mdocs.anthropic.com ↗Epoch AI — internal evaluationsAnthropic system cards and model announcements (lab-reported scores)MathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsLMArena leaderboard datasetmeituan-longcat/LongCat-2.0 model cardARC Prize Foundation model_baseline outputs on ARC-AGI-1/2 public evaluation sets+11
20GPT-5.4 OpenAI78±1api $5.63/M1.1Mplatform.openai.com ↗Epoch AI — internal evaluationsOpenAI vendor-reported benchmark scores for its own models (openai.com announcement posts and Deployment Safety Hub system cards)LMArena leaderboard datasetMathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsARC Prize Foundation model_baseline outputs on ARC-AGI-1/2 public evaluation setsAgents' Last Exam — authors' own fixed-harness model comparison+14
21DeepSeek V4.1 Flash DeepSeek78±1api $0.26/M~537GB1Mapi-docs.deepseek.com ↗Epoch AI — internal evaluationsdeepseek-ai/DeepSeek-V4.1-Flash model cardLMArena leaderboard datasetVideo2World: Benchmarking Coding Agents for Interactive World Modeling from Embodied Videos (arXiv:2610.04432v2)
22Claude Haiku 5.5 Anthropic77±1api $0.20/M1Mplatform.claude.com ↗Epoch AI — internal evaluationsAnthropic system cards and model announcements (lab-reported scores)LMArena leaderboard dataset
23Gemini 3.8 Flash Google77±1api $1.50/M1Mai.google.dev ↗Epoch AI — internal evaluationsMathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsLMArena leaderboard datasetGoogle DeepMind Gemini model page and model cards (lab-reported scores)Google Cloud developer's guides to Gemini 3.8 Flash and 3.7 FlashTerminal-Bench 4.0 official leaderboard submissions+5
24Muse Spark 1.3 Meta77±1api $2.00/M1Mdev.meta.ai ↗Epoch AI — internal evaluationsLMArena leaderboard datasetTerminal-Bench 4.0 official leaderboard submissionsE2E-SWE: Benchmarking LLMs on Building Working Codebases from Scratch (arXiv:2609.38335v1)MathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasets
25Kimi K3 Moonshot AI77±1api $6.00/M~884GB1Mplatform.moonshot.ai ↗Epoch AI — internal evaluationsMathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsLMArena leaderboard datasetGameLogicBench: Evaluating Coding Agents on Runtime Game Logic with Tick-Level State Assertions (arXiv:2609.21562v2)Roblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau Leetcodeτ²/τ³-bench leaderboard: Sierra's own evaluation runs+6
26GPT-5.2 Pro OpenAI77±1api $57.75/M400kdevelopers.openai.com ↗Epoch AI — internal evaluationsARC Prize Foundation model_baseline outputs on ARC-AGI-1/2 public evaluation sets
27MiMo-V2.6-Flash (309B-A15B) Xiaomi77±1api $0.17/M~136GB1Mmimo.mi.com ↗LMArena leaderboard datasetXiaomi MiMo official model cards and documentation
28GPT-6 Luna OpenAI77±1api $0.20/M1.1Mplatform.openai.com ↗Epoch AI — internal evaluationsLMArena leaderboard datasetTerminal-Bench 4.0 official leaderboard submissionsOpenAI vendor-reported benchmark scores for its own models (openai.com announcement posts and Deployment Safety Hub system cards)Roblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau LeetcodeMiðeind Icelandic LLM Leaderboard
29GPT-5.6 Luna OpenAI77±1api $0.45/M1.1Mplatform.openai.com ↗Epoch AI — internal evaluationsOpenAI vendor-reported benchmark scores for its own models (openai.com announcement posts and Deployment Safety Hub system cards)LMArena leaderboard datasetDaekeun Kim Korean LLM benchmark runsTerminal-Bench 4.0 official leaderboard submissionsRoblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau Leetcode+4
30Grok 4.6 SpaceXAI (xAI)77±1api $3.00/M500kdocs.x.ai ↗Epoch AI — internal evaluationsLMArena leaderboard datasetTerminal-Bench 4.0 official leaderboard submissionsRoblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau LeetcodeKlinikeBench: Evaluating Language Models Beyond Diagnostic Accuracy (arXiv:2609.38480v2)
31DeepSeek V4 Pro (0813) DeepSeek76±1api $1.63/M~1010GB1Mdeepinfra.com ↗Epoch AI — internal evaluationsdeepseek-ai/DeepSeek-V4.1-Flash model cardLMArena leaderboard datasetRoblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau LeetcodeGameLogicBench: Evaluating Coding Agents on Runtime Game Logic with Tick-Level State Assertions (arXiv:2609.21562v2)NVIDIA ModelOpt quantized-checkpoint cards: baseline (unquantized) measurements of third-party models+2
32Gemini 3.7 Flash Google76±1api $1.50/M1Mai.google.dev ↗Epoch AI — internal evaluationsMathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsLMArena leaderboard datasetGoogle DeepMind Gemini model page and model cards (lab-reported scores)Google Cloud developer's guides to Gemini 3.8 Flash and 3.7 FlashTerminal-Bench 4.0 official leaderboard submissions+3
33GLM-5.3 Z.ai76±1api $2.15/M~239GB1Mdocs.z.ai ↗Epoch AI — internal evaluationsLMArena leaderboard datasetTerminal-Bench 4.0 official leaderboard submissionsRoblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau Leetcode
34Qwen3.8 Max (0902) Alibaba76±1api $3.00/M1Mwww.alibabacloud.com ↗Epoch AI — internal evaluationsLMArena leaderboard datasetTerminal-Bench 4.0 official leaderboard submissionsVideo2World: Benchmarking Coding Agents for Interactive World Modeling from Embodied Videos (arXiv:2610.04432v2)
38Qwen3.8-Omni-Flash Alibaba75±2†api $0.23/M1Mwww.alibabacloud.com ↗Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)
39Gemini 3.1 Pro (Preview) Google75±1api $4.50/M1Mai.google.dev ↗Epoch AI — internal evaluationsMathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsLMArena leaderboard datasetGoogle DeepMind Gemini model page and model cards (lab-reported scores)meituan-longcat/LongCat-2.0 model cardAgents' Last Exam — authors' own fixed-harness model comparison+23
40Muse Spark 1.2 Meta75±1api $2.00/M1Mdev.meta.ai ↗LMArena leaderboard datasetEpoch AI — internal evaluations
41Claude Opus 4.7 Anthropic75±1api $10.00/M1Mdocs.anthropic.com ↗Epoch AI — internal evaluationsMathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsLMArena leaderboard datasetmeituan-longcat/LongCat-2.0 model cardAnthropic system cards and model announcements (lab-reported scores)Agents' Last Exam — authors' own fixed-harness model comparison+9
42Grok 4.5 SpaceXAI (xAI)75±1api $3.00/M500kdocs.x.ai ↗Epoch AI — internal evaluationsLMArena leaderboard datasetMathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsTerminal-Bench 4.0 official leaderboard submissionsRoblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau Leetcodeτ²/τ³-bench leaderboard: Sierra's own evaluation runs+1
43Muse Spark 1.1 Meta75±1api $2.00/M1Mdev.meta.ai ↗LMArena leaderboard datasetMathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsτ²/τ³-bench leaderboard: Sierra's own evaluation runsEpoch AI — internal evaluations
46Claude Sonnet 5 Anthropic75±1api $4.00/M1Mdocs.anthropic.com ↗Anthropic system cards and model announcements (lab-reported scores)Epoch AI — internal evaluationsLMArena leaderboard datasetDaekeun Kim Korean LLM benchmark runsTerminal-Bench 4.0 official leaderboard submissionsRoblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau Leetcode+5
47Grok 4.7 SpaceXAI (xAI)75±1api $3.00/M500kdocs.x.ai ↗Epoch AI — internal evaluationsLMArena leaderboard datasetKlinikeBench: Evaluating Language Models Beyond Diagnostic Accuracy (arXiv:2609.38480v2)
48Claude Opus 4.6 Anthropic75±1api $10.00/M1Mdocs.anthropic.com ↗Epoch AI — internal evaluationsMathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsLMArena leaderboard datasetAnthropic system cards and model announcements (lab-reported scores)ARC Prize Foundation model_baseline outputs on ARC-AGI-1/2 public evaluation setsAgents' Last Exam — authors' own fixed-harness model comparison+21
49GPT-5.3-Codex OpenAI74±1api $4.81/M400kplatform.openai.com ↗OpenAI vendor-reported benchmark scores for its own models (openai.com announcement posts and Deployment Safety Hub system cards)Epoch AI — internal evaluationsVibe Code Bench (Vals AI, arXiv:2603.04601v3)KlinikeBench: Evaluating Language Models Beyond Diagnostic Accuracy (arXiv:2609.38480v2)
50DeepSeek V4 Flash (0731) DeepSeek74±1api $0.11/M~92GB1Mdeepinfra.com ↗Epoch AI — internal evaluationsdeepseek-ai/DeepSeek-V4.1-Flash model cardDaekeun Kim Korean LLM benchmark runsdeepseek-ai/DeepSeek-V4-Flash-Vision-Exp model cardLMArena leaderboard datasetRoblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau Leetcode+2
51Qwen3.7 Max Alibaba74±1api $3.75/M1Mdeepinfra.com ↗Epoch AI — internal evaluationsLMArena leaderboard datasetAgents' Last Exam — authors' own fixed-harness model comparisonLegal Research Bench (Vals AI, arXiv:2610.00609v1)zai-org/GLM-5.2 model cardEEGAgentBench: Benchmarking LLM Agents on Short- and Long-Horizon EEG Analysis (arXiv:2609.31632v1)
52GLM-5.3-Flash Z.ai74±1api $0.24/M~103GB1Mdocs.z.ai ↗Epoch AI — internal evaluationsLMArena leaderboard datasetzai-org/GLM-5.3-Flash model cardRoblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau LeetcodeTerminal-Bench 4.0 official leaderboard submissionsVideo2World: Benchmarking Coding Agents for Interactive World Modeling from Embodied Videos (arXiv:2610.04432v2)+2
53Gemini 3.5 Flash Google74±1api $3.38/M1Mai.google.dev ↗Epoch AI — internal evaluationsMathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsLMArena leaderboard datasetGoogle DeepMind Gemini model page and model cards (lab-reported scores)Legal Research Bench (Vals AI, arXiv:2610.00609v1)Miðeind Icelandic LLM Leaderboard+3
54GPT-5.2 OpenAI74±1api $4.81/M400kplatform.openai.com ↗Epoch AI — internal evaluationsLMArena leaderboard datasetMathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsDaekeun Kim Korean LLM benchmark runsτ²/τ³-bench leaderboard: Sierra's own evaluation runsARC Prize Foundation model_baseline outputs on ARC-AGI-1/2 public evaluation sets+20
55Hunyuan Hy3 (295B-A21B) Tencent74±1api $0.23/M~96GB256kdeepinfra.com ↗tencent/Hy3 model cardTencent Hy4 preview model cardLMArena leaderboard datasetEEGAgentBench: Benchmarking LLM Agents on Short- and Long-Horizon EEG Analysis (arXiv:2609.31632v1)
56Gemini 3.6 Flash Google74±1api $1.50/M1Mai.google.dev ↗Epoch AI — internal evaluationsMathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsLMArena leaderboard datasetGoogle DeepMind Gemini model page and model cards (lab-reported scores)E2E-SWE: Benchmarking LLMs on Building Working Codebases from Scratch (arXiv:2609.38335v1)Google Cloud developer's guides to Gemini 3.8 Flash and 3.7 Flash+2
57GLM-5.2 Z.ai74±1api $2.15/M~121GB1Mdocs.z.ai ↗Epoch AI — internal evaluationsMathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetszai-org/GLM-5.2 model cardLMArena leaderboard datasetzai-org/GLM-5.3-Flash model cardRoblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau Leetcode+6
59Qwen3.8 27B · 4-bit Alibaba73±1local~22GB262kllama.cpp › Qwen/Qwen3.8-27B model cardLMArena leaderboard datasetQwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)Roblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau LeetcodeBRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)One Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows (arXiv:2608.19741v4)+3
60Grok 4.20 Multi-Agent (0309) SpaceXAI (xAI)73±2api $1.56/M1Mdocs.x.ai ↗LMArena leaderboard dataset
61Kimi K2.6 Moonshot AI73±1api $1.71/M~317GB262kplatform.moonshot.ai ↗Epoch AI — internal evaluationsNVIDIA — Nemotron 3 Ultra technical reportA.X K2 Technical Report (SK Telecom), arXiv 2608.30181v1MathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsLMArena leaderboard datasetAgents' Last Exam — authors' own fixed-harness model comparison+11
62GPT-5 Pro OpenAI73±1api $41.25/M400kdevelopers.openai.com ↗Epoch AI — internal evaluationsOpenAI vendor-reported benchmark scores for its own models (openai.com announcement posts and Deployment Safety Hub system cards)ARC Prize Foundation model_baseline outputs on ARC-AGI-1/2 public evaluation sets
63LongCat 2.0 (1.6T-A48B) Meituan73±2api $1.30/M~2155GB1Mlongcat.chat ↗meituan-longcat/LongCat-2.0 model cardEEGAgentBench: Benchmarking LLM Agents on Short- and Long-Horizon EEG Analysis (arXiv:2609.31632v1)
65GPT-5 OpenAI72±1api $3.44/M400kplatform.openai.com ↗Epoch AI — internal evaluationsLMArena leaderboard datasetOpenAI vendor-reported benchmark scores for its own models (openai.com announcement posts and Deployment Safety Hub system cards)Aider polyglot benchmark runsτ²/τ³-bench leaderboard: Sierra's own evaluation runsKorean Canonical Legal Benchmark: Toward Knowledge-Independent Evaluation of LLMs’ Legal Reasoning Capabilities+22
66Qwen3.6 Max Preview Alibaba72±1api $2.92/M256kwww.alibabacloud.com ↗Epoch AI — internal evaluationsLMArena leaderboard dataset
67Claude Sonnet 4.6 Anthropic72±1api $6.00/M1Mdocs.anthropic.com ↗Anthropic system cards and model announcements (lab-reported scores)Epoch AI — internal evaluationsLMArena leaderboard datasetAgents' Last Exam — authors' own fixed-harness model comparisonKnowledge Index of Noah's Ark (arXiv:2606.05104v2)Legal Research Bench (Vals AI, arXiv:2610.00609v1)+16
68Gemini 3 Flash (Preview) Google72±1api $1.13/M1Mai.google.dev ↗Epoch AI — internal evaluationsLMArena leaderboard datasetτ²/τ³-bench leaderboard: Sierra's own evaluation runsARC Prize Foundation model_baseline outputs on ARC-AGI-1/2 public evaluation setsMathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsGoogle DeepMind Gemini model page and model cards (lab-reported scores)+6
70Claude Opus 4.5 Anthropic72±1api $10.00/M200kdocs.anthropic.com ↗Epoch AI — internal evaluationsLMArena leaderboard datasetτ²/τ³-bench leaderboard: Sierra's own evaluation runsARC Prize Foundation model_baseline outputs on ARC-AGI-1/2 public evaluation setsQwen/Qwen3.6-27B model cardAnthropic system cards and model announcements (lab-reported scores)+13
71Qwen3.7 Plus Alibaba72±1api $0.70/M1Mwww.alibabacloud.com ↗Epoch AI — internal evaluationsQwen/Qwen3.8-27B model cardQwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)LMArena leaderboard datasetSciDocBench: A Workflow-Centered Benchmark and Data Pipeline for Scientific Document Understanding (arXiv:2609.05141v2)SpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models (arXiv:2610.12402v1)
72Kimi K2.7 Code Moonshot AI72±1api $1.71/M~359GB262kplatform.kimi.ai ↗Epoch AI — internal evaluationsLMArena leaderboard dataset
74Grok 4.20 (0309 reasoning) SpaceXAI (xAI)72±1api $1.56/M1Mdocs.x.ai ↗Epoch AI — internal evaluationsLMArena leaderboard datasetARC Prize Foundation model_baseline outputs on ARC-AGI-1/2 public evaluation setsτ²/τ³-bench leaderboard: Sierra's own evaluation runsThe Token Games: Evaluating Language Model Reasoning with Puzzle Duels — authors' own tournamentWildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation (arXiv:2605.10912v1)
76North Small Translate 1.0 Cohere71±6†api price unknown16kdocs.cohere.com ↗Cohere — North Small Translate (arXiv:2609.13916v1)
77GPT-5.4 mini OpenAI71±1api $1.69/M400kplatform.openai.com ↗Epoch AI — internal evaluationsOpenAI vendor-reported benchmark scores for its own models (openai.com announcement posts and Deployment Safety Hub system cards)LMArena leaderboard datasetARC Prize Foundation model_baseline outputs on ARC-AGI-1/2 public evaluation setsDSEffi-Bench: Demystifying Large Language Models' Capability in Efficient Data Science Code Generation — authors' own model runsLegal Research Bench (Vals AI, arXiv:2610.00609v1)+6
78Ling 3.0 Flash (124B-A5B) inclusionAI (Ant Group)71±2†api $0.090/M~80GB131kdeepinfra.com ↗inclusionAI/Ling-3.0-flash model card
79Mistral Large 4 (public preview) Mistral71±2api $2.06/M1Mdocs.mistral.ai ↗LMArena leaderboard datasetEpoch AI — internal evaluations
80GPT-5.1 OpenAI71±1api $3.44/M400kplatform.openai.com ↗Epoch AI — internal evaluationsLMArena leaderboard datasetDaekeun Kim Korean LLM benchmark runsARC Prize Foundation model_baseline outputs on ARC-AGI-1/2 public evaluation setsHyperCLOVA X 32B Think (NAVER Cloud, arXiv:2601.03286v1)OpenAI vendor-reported benchmark scores for its own models (openai.com announcement posts and Deployment Safety Hub system cards)+7
81GLM-5.1 Z.ai71±1api $2.15/M~119GB200kdocs.z.ai ↗NVIDIA — Nemotron 3 Ultra technical reportEpoch AI — internal evaluationsMathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetszai-org/GLM-5.1 model cardzai-org/GLM-5.2 model cardA.X K2 Technical Report (SK Telecom), arXiv 2608.30181v1+11
82Qwen3.5 397B-A17B Alibaba71±0api $1.09/M~65GB262kdeepinfra.com ↗Qwen/Qwen3.5-397B-A17B model cardNVIDIA — Nemotron 3 Ultra technical reportEpoch AI — internal evaluationsQwen/Qwen3.6-27B model cardA.X K2 Technical Report (SK Telecom), arXiv 2608.30181v1LMArena leaderboard dataset+15
83Ornith 1.5 35B-A3B · 4-bit DeepReinforce71±2†local~26GB262kOllama › ornith-ai/Ornith-1.5-35B-A3B model card
84MiniMax-M3 MiniMax70±1api $0.48/M~137GB1Mdeepinfra.com ↗LMArena leaderboard datasetEpoch AI — internal evaluationsLegal Research Bench (Vals AI, arXiv:2610.00609v1)zai-org/GLM-5.2 model cardGameLogicBench: Evaluating Coding Agents on Runtime Game Logic with Tick-Level State Assertions (arXiv:2609.21562v2)Miðeind Icelandic LLM Leaderboard+2
85Grok 4.3 SpaceXAI (xAI)70±1api $1.56/M1Mdocs.x.ai ↗Epoch AI — internal evaluationsLMArena leaderboard datasetAgents' Last Exam — authors' own fixed-harness model comparisonLegal Research Bench (Vals AI, arXiv:2610.00609v1)One Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows (arXiv:2608.19741v4)KlinikeBench: Evaluating Language Models Beyond Diagnostic Accuracy (arXiv:2609.38480v2)
87o3-pro OpenAI70±2api $35.00/M200kdevelopers.openai.com ↗OpenAI vendor-reported benchmark scores for its own models (openai.com announcement posts and Deployment Safety Hub system cards)Aider polyglot benchmark runsOne Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows (arXiv:2608.19741v4)Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
88KAT-Coder-V2.5-Dev (35B-A3B) · 4-bit Kuaishou (Kwaipilot)70±2†local~24GB262kllama.cpp › Kwaipilot/KAT-Coder-V2.5-Dev model card
89Qwen3.6 Plus Alibaba70±1api $1.13/M1Mdocs.together.ai ↗Epoch AI — internal evaluationsLMArena leaderboard datasetQwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)Agents' Last Exam — authors' own fixed-harness model comparisonQwen/Qwen-AgentWorld-35B-A3B model cardBEAR-Bench: A Bilingual Enterprise and Academic Reasoning Benchmark for Multimodal Models (arXiv:2608.17895v1)+1
90Inkling Small (266B-A12B) Thinking Machines70±1api $0.64/M~86GB1Mdeepinfra.com ↗Epoch AI — internal evaluationsthinkingmachines/Inkling-Small model cardLMArena leaderboard datasetMiðeind Icelandic LLM LeaderboardCohere — North Small Translate (arXiv:2609.13916v1)
92Kimi K2.5 Moonshot AI70±1api $1.20/M~160GB262kdocs.aws.amazon.com ↗Epoch AI — internal evaluationsLMArena leaderboard datasetstepfun-ai/Step-3.5-Flash model cardMathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsARC Prize Foundation model_baseline outputs on ARC-AGI-1/2 public evaluation setsQwen/Qwen3.5-397B-A17B model card+15
93GLM-5 Z.ai70±1api $1.55/M~119GB205kdocs.z.ai ↗zai-org/GLM-5.1 model cardMathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsGLM-5 Team (Zhipu AI) — GLM-5 technical reportEpoch AI — internal evaluationszai-org/GLM-5 model cardLMArena leaderboard dataset+11
95MiMo-V2.5-Pro (1T-A42B) Xiaomi70±1api $0.65/M~163GB1Mnovita.ai ↗LMArena leaderboard datasetXiaomiMiMo/MiMo-V2.5-Pro model cardXiaomi MiMo official model cards and documentationGameLogicBench: Evaluating Coding Agents on Runtime Game Logic with Tick-Level State Assertions (arXiv:2609.21562v2)WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation (arXiv:2605.10912v1)EEGAgentBench: Benchmarking LLM Agents on Short- and Long-Horizon EEG Analysis (arXiv:2609.31632v1)
96Inkling (975B-A41B) Thinking Machines70±1api $1.73/M~156GB1Mdeepinfra.com ↗Epoch AI — internal evaluationsthinkingmachines/Inkling-Small model cardLMArena leaderboard datasetτ²/τ³-bench leaderboard: Sierra's own evaluation runsMiðeind Icelandic LLM Leaderboard
97Muse Glimmer 30B · 4-bit Meta70±1local~21GB131kOllama › meta-models/Muse-Glimmer-30B model card (speed and benchmark tables)LMArena leaderboard datasetRoblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau LeetcodeQwen/Qwen3.8-27B model cardSpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)Cohere — North Small Translate (arXiv:2609.13916v1)
98Nemotron 3 Ultra 550B-A55B NVIDIA69±1api $1.35/M~89GB1Mdocs.together.ai ↗NVIDIA — Nemotron 3 Ultra technical reportA.X K2 Technical Report (SK Telecom), arXiv 2608.30181v1Epoch AI — internal evaluationsLMArena leaderboard datasetCohere — North Small Translate (arXiv:2609.13916v1)
99Qwen3.6 27B · 4-bit Alibaba69±1local~22GB262kllama.cpp › Qwen/Qwen3.6-27B model cardEpoch AI — internal evaluationsQwen/Qwen3.8-27B model cardmeta-models/Muse-Glimmer-30B model card (speed and benchmark tables)Roblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau LeetcodeOne Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows (arXiv:2608.19741v4)+4
102o3 OpenAI69±1api $3.50/M200kplatform.openai.com ↗Epoch AI — internal evaluationsMeituan LongCat-Flash-Thinking model card (evaluation table)Qwen/Qwen3-235B-A22B-Thinking-2507 model cardOpenAI simple-evals README benchmark results (OpenAI's own models)OpenAI vendor-reported benchmark scores for its own models (openai.com announcement posts and Deployment Safety Hub system cards)LMArena leaderboard dataset+11
103MiMo-V2.5 (310B-A15B) Xiaomi69±1api $0.21/M~100GB1Mnovita.ai ↗Solar Open 2 Technical Report (Upstage, arXiv:2607.20062v2)LMArena leaderboard datasetXiaomiMiMo/MiMo-V2.5 model cardAgents' Last Exam — authors' own fixed-harness model comparisonXiaomi MiMo vendor-reported benchmark scores for its own models (mimo.xiaomi.com launch pages)SciDocBench: A Workflow-Centered Benchmark and Data Pipeline for Scientific Document Understanding (arXiv:2609.05141v2)
104Qwen3.5 Plus Alibaba69±2api $0.90/M1Mwww.alibabacloud.com ↗Epoch AI — internal evaluationsVibe Code Bench (Vals AI, arXiv:2603.04601v3)Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
105Qwen3.5 122B-A10B Alibaba69±1api $1.10/M~79GB262kwww.alibabacloud.com ↗Qwen/Qwen3.5-122B-A10B model cardQwen/Qwen3.5-27B model cardLMArena leaderboard datasetKnowledge Index of Noah's Ark (arXiv:2606.05104v2)Reassessing High-Performing LLMs on Polish Medical Exams: True Competence or Bias-Driven Performance? (arXiv:2606.12250v1)Epoch AI — internal evaluations+5
106Gemini 3.5 Flash-Lite Google69±1api $0.85/M1Mai.google.dev ↗Epoch AI — internal evaluationsLMArena leaderboard datasetGoogle DeepMind Gemini model page and model cards (lab-reported scores)Miðeind Icelandic LLM Leaderboard
107GLM-4.7 Z.ai69±1api $1.00/M~58GB205kdocs.z.ai ↗zai-org/GLM-4.7 model cardGLM-5 Team (Zhipu AI) — GLM-5 technical reportzai-org/GLM-5 model cardLMArena leaderboard datasetEpoch AI — internal evaluationsMedmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 models+5
109GPT-5.4 nano OpenAI69±1api $0.46/M400kplatform.openai.com ↗Epoch AI — internal evaluationsOpenAI vendor-reported benchmark scores for its own models (openai.com announcement posts and Deployment Safety Hub system cards)LMArena leaderboard datasetARC Prize Foundation model_baseline outputs on ARC-AGI-1/2 public evaluation setsRoblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau LeetcodeT1-Bench: Benchmarking Multi-Scenario Agents in Real-World Domains (arXiv:2606.11070v1)+1
110Claude Sonnet 4.5 Anthropic69±1api $6.00/M200kdocs.anthropic.com ↗Epoch AI — internal evaluationsServiceNow-AI/Apriel-1.6-15b-Thinker model cardLMArena leaderboard datasetMedmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 modelsτ²/τ³-bench leaderboard: Sierra's own evaluation runsARC Prize Foundation model_baseline outputs on ARC-AGI-1/2 public evaluation sets+18
111Qwen3.5 27B · 4-bit Alibaba69±0local~20GB262kOllama › Qwen/Qwen3.5-122B-A10B model cardQwen/Qwen3.6-35B-A3B model cardQwen/Qwen3.6-27B model cardQwen/Qwen3.5-27B model cardKwaipilot/KAT-Coder-V2.5-Dev model cardLMArena leaderboard dataset+8
112GLM-5V-Turbo Z.ai69±2api $1.90/M200kwww.siliconflow.com ↗LMArena leaderboard dataset
115Step 3.5 Flash (196B-A11B) StepFun68±1api $0.15/M~126GB256kplatform.stepfun.ai ↗MathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsstepfun-ai/Step-3.5-Flash model cardLMArena leaderboard datasetKnowledge Index of Noah's Ark (arXiv:2606.05104v2)WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation (arXiv:2605.10912v1)
116DeepSeek V3.2 DeepSeek68±1api $0.29/M~110GB128kdeepinfra.com ↗LMArena leaderboard datasetEpoch AI — internal evaluationsdeepseek-ai/DeepSeek-V3.2 model cardMathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsARC Prize Foundation model_baseline outputs on ARC-AGI-1/2 public evaluation setsstepfun-ai/Step-3.5-Flash model card+15
120MiniMax-M2.7 MiniMax68±1api $0.53/M~75GB205kplatform.minimax.io ↗NVIDIA — Nemotron 3 Ultra technical reportA.X K2 Technical Report (SK Telecom), arXiv 2608.30181v1LMArena leaderboard datasetinclusionAI/Ling-3.0-flash model cardQwen/Qwen-AgentWorld-35B-A3B model cardWildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation (arXiv:2605.10912v1)+2
121Qwen3.6 35B-A3B · 4-bit Alibaba68±1local~24GB262kOllama › Qwen/Qwen3.6-27B model cardQwen/Qwen3.6-35B-A3B model cardEpoch AI — internal evaluationsMathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsKwaipilot/KAT-Coder-V2.5-Dev model cardRoblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau Leetcode+4
122Ornith 1.0 35B (35B-A3B) · 4-bit DeepReinforce68±1local~24GB262kllama.cpp › ornith-ai/Ornith-1.5-35B-A3B model cardKwaipilot/KAT-Coder-V2.5-Dev model card
124GPT-5 mini OpenAI67±1api $0.69/M400kplatform.openai.com ↗Epoch AI — internal evaluationsOpenAI vendor-reported benchmark scores for its own models (openai.com announcement posts and Deployment Safety Hub system cards)ServiceNow-AI/Apriel-1.6-15b-Thinker model cardDaekeun Kim Korean LLM benchmark runsServiceNow BrowserGym leaderboard (AgentLab GenericAgent runs)LMArena leaderboard dataset+16
125Gemini 2.5 Pro Google67±1api $3.44/M1Mai.google.dev ↗Meituan LongCat-Flash-Thinking model card (evaluation table)Epoch AI — internal evaluationsLMArena leaderboard datasetGoogle DeepMind Gemini model page and model cards (lab-reported scores)Roblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau LeetcodeKorean Canonical Legal Benchmark: Toward Knowledge-Independent Evaluation of LLMs’ Legal Reasoning Capabilities+16
129Kimi K2 Thinking Moonshot AI67±1api $1.07/M~160GB262kdocs.aws.amazon.com ↗LMArena leaderboard datasetEpoch AI — internal evaluationsstepfun-ai/Step-3.5-Flash model cardTerminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces — benchmark authors' own agent-model trialsWebApp1K models leaderboard (onekq-ai)
130Laguna M.1 Poolside67±2api price unknown~144GB262khuggingface.co ↗LMArena leaderboard datasetPoolside — Laguna M.1/XS.2 Technical Report
131Qwen3.7 Flash Alibaba67±1api $0.055/M1Mwww.alibabacloud.com ↗Epoch AI — internal evaluations
132Step 3.7 Flash (198B-A11B) StepFun67±1api $0.44/M~104GB256kplatform.stepfun.ai ↗MathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsinclusionAI/Ling-3.0-flash model card
133Gemma 4 31B · 4-bit Google67±1local~21GB262kOllama › Gemma Team — Gemma 4 Technical ReportKwaipilot/KAT-Coder-V2.5-Dev model cardmeta-models/Muse-Glimmer-30B model card (speed and benchmark tables)LMArena leaderboard datasetEpoch AI — internal evaluationsQwen/Qwen3.6-35B-A3B model card+20
134Gemini 3.1 Flash-Lite Google67±1api $0.56/M1Mai.google.dev ↗Epoch AI — internal evaluationsLMArena leaderboard datasetGoogle DeepMind Gemini model page and model cards (lab-reported scores)K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts (arXiv:2606.02404v1)MathConstraint: Automated Generation of Verified Combinatorial Reasoning Instances for LLMs — authors' own model runsVectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
135Qwen3-Coder-Next (80B-A3B) · 2-bit Alibaba67±2local~27GB262kllama.cpp › Vector Institute Evaluation Leaderboard (Inspect Evals runs)DSEffi-Bench: Demystifying Large Language Models' Capability in Efficient Data Science Code Generation — authors' own model runs
139Qwen3.5 35B-A3B · 4-bit Alibaba67±0local~25GB262kOllama › Qwen/Qwen3.5-122B-A10B model cardQwen/Qwen3.6-35B-A3B model cardQwen/Qwen3.5-27B model cardKwaipilot/KAT-Coder-V2.5-Dev model cardNVIDIA — Nemotron-Cascade 2 technical reportLMArena leaderboard dataset+12
142Qwen3 235B-A22B Thinking 2507 Alibaba66±1api $0.97/M~76GB131knovita.ai ↗Meituan LongCat-Flash-Thinking model card (evaluation table)Qwen/Qwen3-235B-A22B-Thinking-2507 model cardQwen/Qwen3-Next-80B-A3B-Thinking model cardQwen3-VL-235B-A22B-Thinking model cardQwen/Qwen3.5-27B model cardEpoch AI — internal evaluations+6
143Grok 4.1 Fast (Reasoning) SpaceXAI (xAI)66±1api $0.28/M128kazure.microsoft.com ↗LMArena leaderboard datasetMathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsKnowledge Index of Noah's Ark (arXiv:2606.05104v2)τ²/τ³-bench leaderboard: Sierra's own evaluation runsBerkeley Function Calling Leaderboard result archiveWebApp1K models leaderboard (onekq-ai)+4
144o4-mini OpenAI66±1api $1.93/M200kplatform.openai.com ↗Epoch AI — internal evaluationsQwen/Qwen3-235B-A22B-Thinking-2507 model cardOpenAI simple-evals README benchmark results (OpenAI's own models)Aider polyglot benchmark runsLMArena leaderboard datasetArena-Hard-Auto v2.0-Preview leaderboard (repository README)+12
145Qwen3.6 Flash Alibaba66±1api $0.56/M1Mwww.alibabacloud.com ↗Epoch AI — internal evaluationsSpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models (arXiv:2610.12402v1)
147GLM-4.6 Z.ai66±1api $1.00/M~58GB205kdocs.z.ai ↗zai-org/GLM-4.7 model cardzai-org/GLM-4.6 model cardLMArena leaderboard datasetTerminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces — benchmark authors' own agent-model trialsBerkeley Function Calling Leaderboard result archiveWebApp1K models leaderboard (onekq-ai)+1
148Kimi K2 Instruct (0711) Moonshot AI66±1api $1.00/M~160GB131knovita.ai ↗Meituan LongCat-Flash-Chat model card (evaluation table)Aider polyglot benchmark runsMoonshot AI Kimi-K2-Instruct model card (instruction-model evaluation table)LMArena leaderboard datasetEQ-Bench 3 canonical leaderboard resultsBerkeley Function Calling Leaderboard result archive+3
149o1 (2024-12-17) OpenAI66±1api $26.25/M200kdevelopers.openai.com ↗Epoch AI — internal evaluationsOpenAI simple-evals README benchmark results (OpenAI's own models)Vector Institute Evaluation Leaderboard (Inspect Evals runs)Aider polyglot benchmark runsLiveCodeBench official website results (2024-12-26)WildEval ZeroEval published results+13
150MiniMax-M2.5 MiniMax66±1api $0.53/M~75GB205kplatform.minimax.io ↗LMArena leaderboard datasetARC Prize Foundation model_baseline outputs on ARC-AGI-1/2 public evaluation setsContractBench: Can LLM Agents Preserve Observation Contracts? (arXiv:2605.17281v2)DSEffi-Bench: Demystifying Large Language Models' Capability in Efficient Data Science Code Generation — authors' own model runsKnowledge Index of Noah's Ark (arXiv:2606.05104v2)WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation (arXiv:2605.10912v1)+3
151Qwen3-Max (2025-09-23) Alibaba66±1api $2.40/M262kwww.alibabacloud.com ↗Epoch AI — internal evaluationsτ²-bench leaderboard: Qwen (Alibaba) own submissionsLMArena leaderboard datasetKnowledge Index of Noah's Ark (arXiv:2606.05104v2)
152DeepSeek V3.1 DeepSeek66±1api $0.42/M~110GB131kdeepinfra.com ↗Meituan LongCat-Flash-Thinking model card (evaluation table)Meituan LongCat-Flash-Chat model card (evaluation table)deepseek-ai/DeepSeek-V3.1 model cardDeepSeek-V3.1-Terminus model cardLMArena leaderboard datasetRPC-Bench leaderboard (Z.ai research paper comprehension)+3
153Spark-X2.5 4B · 16-bit iFLYTEK (SparkLLM)66±1†local~10GB1MOllama › XHToken/Spark-X2.5-4B model card
155Nemotron Cascade 2 30B-A3B · 4-bit NVIDIA66±1local~27GB256kllama.cpp › NVIDIA — Nemotron-Cascade 2 technical reportEuroEval leaderboards (results collection), English generative leaderboard
156Laguna XS 2.1 (33B-A3B) · 4-bit Poolside66±2†local~23GB262kllama.cpp › Poolside vendor-reported benchmark scores for its own Laguna models (Hugging Face model cards)
158o3-mini OpenAI65±1api $1.93/M200kdevelopers.openai.com ↗Epoch AI — internal evaluationsServiceNow-AI/Apriel-1.6-15b-Thinker model cardMicrosoft — Phi-4-reasoning Technical ReportOpenAI simple-evals README benchmark results (OpenAI's own models)Vector Institute Evaluation Leaderboard (Inspect Evals runs)Aider polyglot benchmark runs+13
161MiMo-V2.6-Distill-Qwen-9B · 8-bit Xiaomi65±2†local~12GBllama.cpp › XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B model card
163DeepSeek R1 0528 DeepSeek65±1api $0.91/M~110GB164kdeepinfra.com ↗deepseek-ai/DeepSeek-R1-0528 model cardPrime Intellect INTELLECT-3 model card: Evaluation table (Environments Hub runs)deepseek-ai/DeepSeek-V3.1 model cardServiceNow-AI/Apriel-1.6-15b-Thinker model cardEpoch AI — internal evaluationsAider polyglot benchmark runs+6
164EXAONE 4.5 33B · 4-bit LG AI Research65±2†local~24GB262kllama.cpp › LG AI Research vendor-reported benchmark scores for its own EXAONE models (Hugging Face model cards)
165Qwen3.5 Flash Alibaba65±1api $0.17/M1Mwww.alibabacloud.com ↗Epoch AI — internal evaluationsLMArena leaderboard datasetVectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
167INTELLECT-3 · 2-bit Prime Intellect65±1local (slow)~48GBllama.cpp › Prime Intellect INTELLECT-3 model card: Evaluation table (Environments Hub runs)Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 modelsLMArena leaderboard dataset
168Nemotron 3 Super 120B-A12B NVIDIA65±1api $0.28/M~78GB262kdocs.aws.amazon.com ↗NVIDIA vendor-reported benchmark scores for its own Nemotron models (Hugging Face model cards)NVIDIA — Nemotron-Cascade 2 technical reportMathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsLMArena leaderboard datasetinclusionAI/Ling-3.0-flash model card
169GLM-4.5 Z.ai65±1api $1.00/M~58GB131kdocs.z.ai ↗Meituan LongCat-Flash-Thinking model card (evaluation table)GLM-4.5 Team (Zhipu AI & Tsinghua) — GLM-4.5 technical reportPrime Intellect INTELLECT-3 model card: Evaluation table (Environments Hub runs)zai-org/GLM-4.6 model cardLMArena leaderboard datasetEQ-Bench 3 canonical leaderboard results+3
170Solar Pro 4 Upstage65±2api $0.53/M524kdevelopers.upstage.ai ↗LMArena leaderboard dataset
171MiniMax-M2 MiniMax65±1api $0.53/M~75GB205kdocs.aws.amazon.com ↗LMArena leaderboard datasetMedmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 modelsContractBench: Can LLM Agents Preserve Observation Contracts? (arXiv:2605.17281v2)MiniMax vendor-reported benchmark scores for its own models (Hugging Face model cards)Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces — benchmark authors' own agent-model trials
172Laguna XS.2 · 4-bit Poolside65±2local~26GB262kOllama › Poolside vendor-reported benchmark scores for its own Laguna models (Hugging Face model cards)LMArena leaderboard datasetPoolside — Laguna M.1/XS.2 Technical Report
173Qwen3 235B-A22B Instruct 2507 Alibaba65±1api $0.20/M~76GB262kdeepinfra.com ↗Qwen/Qwen3-Next-80B-A3B-Instruct model cardMeituan LongCat-Flash-Chat model card (evaluation table)Qwen3-VL-235B-A22B-Instruct model cardQwen/Qwen3-235B-A22B-Instruct-2507 model cardARC Prize Foundation model_baseline outputs on ARC-AGI-1/2 public evaluation setsLMArena leaderboard dataset+3
174Mistral Medium 3.5 (128B) Mistral65±1api $3.00/M +local~42GB262kdocs.mistral.ai ↗Solar Open 2 Technical Report (Upstage, arXiv:2607.20062v2)LMArena leaderboard datasetCohere — North Small Translate (arXiv:2609.13916v1)Miðeind Icelandic LLM LeaderboardEEGAgentBench: Benchmarking LLM Agents on Short- and Long-Horizon EEG Analysis (arXiv:2609.31632v1)
175Command A+ (05-2026) Cohere64±1api price unknown~71GB128kdocs.cohere.com ↗Solar Open 2 Technical Report (Upstage, arXiv:2607.20062v2)Cohere vendor-reported benchmark scores for its own models (cohere.com blog)Cohere — North Small Translate (arXiv:2609.13916v1)
176Claude Haiku 4.5 Anthropic64±1api $2.00/M200kdocs.anthropic.com ↗Anthropic system cards and model announcements (lab-reported scores)Epoch AI — internal evaluationsLMArena leaderboard datasetRoblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau LeetcodeARC Prize Foundation model_baseline outputs on ARC-AGI-1/2 public evaluation setsTerminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces — benchmark authors' own agent-model trials+9
177Nemotron-Labs-3 Puzzle 75B-A9B · 2-bit NVIDIA64±1†local (slow)~35GBllama.cpp › NVIDIA vendor-reported benchmark scores for its own Nemotron models (Hugging Face model cards)
179Qwen3-Coder 480B-A35B Instruct Alibaba64±1api $0.67/M~78GB262knovita.ai ↗Qwen/Qwen3-Coder-30B-A3B-Instruct model cardLMArena leaderboard datasetTerminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces — benchmark authors' own agent-model trialsWebApp1K models leaderboard (onekq-ai)
181Gemma 4 26B-A4B · 8-bit Google64±1local~30GB262kllama.cpp › Gemma Team — Gemma 4 Technical Reportgoogle/diffusiongemma-26B-A4B-it model cardKwaipilot/KAT-Coder-V2.5-Dev model cardLMArena leaderboard datasetEpoch AI — internal evaluationsRoblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau Leetcode+12
184Nova 2 Pro (Preview) Amazon64±2api $3.78/M1Maws.amazon.com ↗Daekeun Kim Korean LLM benchmark runsAmazon AGI — τ²-Bench-Verified
186MiniCPM5 2B · 8-bit OpenBMB64±1†local~4.3GB131kllama.cpp › openbmb/MiniCPM5-2B model card
188Qwen3-Next 80B-A3B Thinking · 2-bit Alibaba63±1local~27GB131kllama.cpp › Qwen/Qwen3-Next-80B-A3B-Thinking model cardQwen/Qwen3.5-9B model cardQwen/Qwen3.5-4B model cardMedmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 modelsLMArena leaderboard datasetKnowledge Index of Noah's Ark (arXiv:2606.05104v2)+3
189DeepSeek R1 (Jan '25) DeepSeek63±1api $4.00/M~110GB128kdocs.together.ai ↗deepseek-ai/DeepSeek-R1 model carddeepseek-ai/DeepSeek-R1-0528 model cardEpoch AI — internal evaluationsVector Institute Evaluation Leaderboard (Inspect Evals runs)Aider polyglot benchmark runsWildEval ZeroEval published results+15
191Qwen3-Next 80B-A3B Instruct · 2-bit Alibaba63±1local~27GB131kllama.cpp › Qwen/Qwen3-Next-80B-A3B-Instruct model cardMedmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 modelsLMArena leaderboard datasetKnowledge Index of Noah's Ark (arXiv:2606.05104v2)BRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)EuroEval leaderboards (results collection), English generative leaderboard
192Granite 4.2 30B · 4-bit IBM63±1local~21GB131kOllama › ibm-granite/granite-4.2-30b model cardLMArena leaderboard dataset
195GLM-4.5-Air Z.ai63±1api $0.42/M +local~35GB131kdocs.z.ai ↗GLM-4.5 Team (Zhipu AI & Tsinghua) — GLM-4.5 technical reportPrime Intellect INTELLECT-3 model card: Evaluation table (Environments Hub runs)Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 modelsLMArena leaderboard datasetSolar Open Technical Report (arXiv:2601.07022v1)Berkeley Function Calling Leaderboard result archive+3
196Qwen3.5 9B · 8-bit Alibaba63±1local~12GB262kllama.cpp › Qwen/Qwen3.5-9B model cardXHToken/Spark-X2.5-4B model cardJetBrains/Mellum2.1-12B-A2.5B-Thinking model cardJetBrains/Mellum2-12B-A2.5B-Instruct model cardEpoch AI — internal evaluationsQwen/Qwen3.5-4B model card+17
197Seed-OSS 36B Instruct · 4-bit ByteDance Seed63±1local~25GB524kllama.cpp › ByteDance-Seed/Seed-OSS-36B-Instruct model cardEpoch AI — internal evaluations
199Trinity-Large-Thinking Arcee AI63±2api $0.39/M~141GB512kdocs.arcee.ai ↗LMArena leaderboard datasetArcee AI vendor-reported benchmark scores for its own Trinity models (Hugging Face model cards)
201MiniMax-M1 (80k) MiniMax62±1api $0.96/M~959GB1Mnovita.ai ↗MiniMaxAI/MiniMax-M1-80k model cardLMArena leaderboard dataset
202Gemma 4 12B · 8-bit Google62±1local~15GB262kllama.cpp › Gemma Team — Gemma 4 Technical ReportXHToken/Spark-X2.5-4B model cardgoogle/gemma-4-31B-it model card
203GPT-4.1 OpenAI62±1api $3.50/M1Mplatform.openai.com ↗Meituan LongCat-Flash-Chat model card (evaluation table)Epoch AI — internal evaluationsOpenAI simple-evals README benchmark results (OpenAI's own models)Aider polyglot benchmark runsDaekeun Kim Korean LLM benchmark runsMUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool use (arXiv:2508.18669v1)+17
204Nemotron 3.5 Lightning 30B-A3B · 4-bit NVIDIA62±2local~28GB262kllama.cpp › Roblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau LeetcodeLMArena leaderboard dataset
205GLM-4.6V Z.ai62±2api $0.45/M +local~51GB128kdocs.z.ai ↗LMArena leaderboard datasetZ.ai GLM-V GitHub repository benchmark image (GLM-4.6V)SciDocBench: A Workflow-Centered Benchmark and Data Pipeline for Scientific Document Understanding (arXiv:2609.05141v2)
209gpt-oss-120b OpenAI62±1api $0.26/M~67GB131kconsole.groq.com ↗OpenAI — gpt-oss-120b & gpt-oss-20b Model CardPrime Intellect INTELLECT-3 model card: Evaluation table (Environments Hub runs)ServiceNow-AI/Apriel-1.6-15b-Thinker model cardEpoch AI — internal evaluationsAider polyglot benchmark runsMedmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 models+19
210GPT-5 nano OpenAI62±1api $0.14/M400kplatform.openai.com ↗Epoch AI — internal evaluationsDaekeun Kim Korean LLM benchmark runsLMArena leaderboard datasetServiceNow BrowserGym leaderboard (AgentLab GenericAgent runs)Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces — benchmark authors' own agent-model trialsOpenAI vendor-reported benchmark scores for its own models (openai.com announcement posts and Deployment Safety Hub system cards)+7
211Qwen3-VL 32B Thinking · 4-bit Alibaba62±1local~24GB256kOllama › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)HyperCLOVA X 32B Think (NAVER Cloud, arXiv:2601.03286v1)allenai/Olmo-3.1-32B-Think model card
213Mistral Large 3 (675B-A41B) Mistral62±1api $0.75/M~108GB262kdocs.mistral.ai ↗LMArena leaderboard datasetmistralai/Mistral-Small-4-119B-2603 model cardCohere — North Small Translate (arXiv:2609.13916v1)LongSocialBench: Do Long-Context LLMs Understand Online Discussion Threads? (arXiv:2610.04118v1)Miðeind Icelandic LLM LeaderboardOne Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows (arXiv:2608.19741v4)+1
214Apriel 1.6 15B Thinker · 8-bit ServiceNow62±2†local~21GBllama.cpp › ServiceNow-AI/Apriel-1.6-15b-Thinker model card
216Gemini 2.5 Flash Google62±1api $0.85/M1Mai.google.dev ↗Meituan LongCat-Flash-Chat model card (evaluation table)LMArena leaderboard datasetGoogle DeepMind Gemini model page and model cards (lab-reported scores)Korean Canonical Legal Benchmark: Toward Knowledge-Independent Evaluation of LLMs’ Legal Reasoning CapabilitiesContractBench: Can LLM Agents Preserve Observation Contracts? (arXiv:2605.17281v2)Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces — benchmark authors' own agent-model trials+10
219GLM-4.5V Z.ai61±2api $0.90/M~69GB64kdocs.z.ai ↗Z.ai GLM-V GitHub repository benchmark image (GLM-4.6V)LMArena leaderboard datasetServiceNow-AI/Apriel-1.6-15b-Thinker model cardChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)
222Devstral Small 2 24B · 8-bit Mistral61±3†local~28GB262kllama.cpp › mistralai/Devstral-Small-2-24B-Instruct-2512 model card
225Qwen3 30B-A3B Thinking 2507 · 4-bit Alibaba61±1local~21GB262kOllama › Qwen/Qwen3-Next-80B-A3B-Thinking model cardQwen/Qwen3-30B-A3B-Thinking-2507 model cardByteDance-Seed/Seed-OSS-36B-Instruct model cardQwen/Qwen3.5-9B model cardEpoch AI — internal evaluationsQwen/Qwen3.5-4B model card+8
226Qwen3.5 4B · 8-bit Alibaba61±1local~6.2GB262kllama.cpp › Qwen/Qwen3.5-9B model cardopenbmb/MiniCPM5-2B model cardXHToken/Spark-X2.5-4B model cardJetBrains/Mellum2-12B-A2.5B-Instruct model cardQwen/Qwen3.5-4B model cardLiquidAI/LFM2.5-2.6B model card+10
227Nemotron-Cascade-14B-Thinking · 8-bit NVIDIA61±1†local~18GBllama.cpp › NVIDIA — Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
228Mellum2.1 12B-A2.5B Thinking · 16-bit JetBrains60±2†local~27GBhow to run › JetBrains/Mellum2.1-12B-A2.5B-Thinking model card
229GPT-4.1 mini OpenAI60±1api $0.70/M1Mplatform.openai.com ↗Epoch AI — internal evaluationsOpenAI simple-evals README benchmark results (OpenAI's own models)Daekeun Kim Korean LLM benchmark runsAider polyglot benchmark runsOpenAI vendor-reported benchmark scores for its own models (openai.com announcement posts and Deployment Safety Hub system cards)Arena-Hard-Auto v2.0-Preview leaderboard (repository README)+13
231Qwen3 30B-A3B Instruct 2507 · 4-bit Alibaba60±1local~21GB262kOllama › Qwen/Qwen3-Next-80B-A3B-Instruct model cardQwen/Qwen3-30B-A3B-Instruct-2507 model cardEpoch AI — internal evaluationsLMArena leaderboard datasetMedmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 modelsBRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)+4
232Qwen3-VL 32B Instruct · 4-bit Alibaba60±1†local~24GB256kOllama › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)
233Falcon-H1R 7B · 8-bit TII60±1†local~12GB262kllama.cpp › Falcon-H1R: Pushing the Reasoning Frontiers with a Hybrid Model for Efficient Test-Time Scaling
237Qwen3 235B-A22B (Apr 2025, hybrid) Alibaba60±1api $1.23/M~76GB131kwww.alibabacloud.com ↗Qwen/Qwen3-235B-A22B-Thinking-2507 model cardQwen/Qwen3-30B-A3B-Thinking-2507 model cardQwen/Qwen3-30B-A3B-Instruct-2507 model cardQwen/Qwen3-235B-A22B-Instruct-2507 model cardEpoch AI — internal evaluationsAider polyglot benchmark runs+14
239Granite 4.2 8B · 8-bit IBM60±1local~11GB131kllama.cpp › ibm-granite/granite-4.2-30b model cardLMArena leaderboard dataset
240Solar Open 100B (102B-A12B) · 2-bit Upstage60±1†local (slow)~41GB131kllama.cpp › Solar Open 2 Technical Report (Upstage, arXiv:2607.20062v2)Solar Open Technical Report (arXiv:2601.07022v1)
241Qwen3-VL 30B-A3B Thinking · 4-bit Alibaba60±1†local~23GB256kOllama › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)
242Mistral Small 4 (119B-A6.5B) Mistral60±2api $0.26/M +local~40GB262kdocs.mistral.ai ↗mistralai/Mistral-Small-4-119B-2603 model cardContractBench: Can LLM Agents Preserve Observation Contracts? (arXiv:2605.17281v2)Inception Arabic/Hindi leaderboards (AraGen-v3, HindiGen-v1, Arabic IFEval)Miðeind Icelandic LLM Leaderboard
244QwQ-32B · 4-bit Alibaba59±1local~23GB131kOllama › Epoch AI — internal evaluations2 OLMo 2 Furious (Team OLMo, Ai2) — authors' own evaluations of OLMo 2 Instruct and peer instruct modelsAider polyglot benchmark runsArena-Hard-Auto v2.0-Preview leaderboard (repository README)LMArena leaderboard datasetWebApp1K models leaderboard (onekq-ai)+7
245OpenReasoning-Nemotron-32B · 4-bit NVIDIA59±2†local~22GBllama.cpp › NVIDIA — Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
246DeepSeek V3 (Dec '24) DeepSeek59±1api $0.46/M~337GB131kdeepinfra.com ↗deepseek-ai/DeepSeek-R1 model cardCohere — Command A technical reportEpoch AI — internal evaluationsLiveCodeBench official website results (2024-12-26)Aider polyglot benchmark runsWildEval ZeroEval published results+10
247Gemma 2 9B IT SimPO · 16-bit Princeton NLP59±1local~21GBhow to run › AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)WildBench v2 leaderboard data (Ai2)LMArena leaderboard datasetOpen Portuguese LLM Leaderboard (archived)
248Gemma 2 9B IT DPO (Princeton) · 16-bit Princeton NLP59±1local~21GBhow to run › AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)WildBench v2 leaderboard data (Ai2)Open Portuguese LLM Leaderboard (archived)
250GLM-4.7-Flash · 4-bit Z.ai59±1local~22GB200kOllama › Epoch AI — internal evaluationsRoblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau LeetcodeLMArena leaderboard datasetEuroEval leaderboards (results collection), English generative leaderboardEQ-Bench 3 canonical leaderboard resultsVectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
251EXAONE 4.0 32B · 4-bit LG AI Research59±1local~22GB131kllama.cpp › LG AI Research vendor-reported benchmark scores for its own EXAONE models (Hugging Face model cards)HyperCLOVA X 32B Think (NAVER Cloud, arXiv:2601.03286v1)Korean Canonical Legal Benchmark: Toward Knowledge-Independent Evaluation of LLMs’ Legal Reasoning CapabilitiesEuroEval leaderboards (results collection), English generative leaderboard
252Phi-4-reasoning-plus 14B · 8-bit Microsoft59±1local~18GBllama.cpp › Falcon-H1R: Pushing the Reasoning Frontiers with a Hybrid Model for Efficient Test-Time ScalingMicrosoft — Phi-4-reasoning Technical Reportmicrosoft/Phi-4-reasoning model cardEuroEval leaderboards (results collection), English generative leaderboardOpen Portuguese LLM Leaderboard (archived)
253Nemotron-Cascade-8B · 8-bit NVIDIA59±1†local~11GBllama.cpp › NVIDIA — Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
254Qwen3 14B · 8-bit Alibaba59±1local~21GB33kOllama › Epoch AI — internal evaluationsMUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool use (arXiv:2508.18669v1)Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 modelsBerkeley Function Calling Leaderboard result archiveBRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)Inception Arabic/Hindi leaderboards (AraGen-v3, HindiGen-v1, Arabic IFEval)+6
257gpt-oss-20b · MXFP4 OpenAI58±1local~15GB131kOllama › Falcon-H1R: Pushing the Reasoning Frontiers with a Hybrid Model for Efficient Test-Time ScalingByteDance-Seed/Seed-OSS-36B-Instruct model cardOpenAI — gpt-oss-120b & gpt-oss-20b Model CardEpoch AI — internal evaluationsMedmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 modelsServiceNow BrowserGym leaderboard (AgentLab GenericAgent runs)+15
258Llama 3.3 Nemotron Super 49B v1 · 2-bit NVIDIA58±2local~22GBllama.cpp › NVIDIA — Llama-Nemotron: Efficient Reasoning ModelsLMArena leaderboard dataset
259Olmo 3.1 32B Think · 4-bit Ai258±1local~22GB66kOllama › Olmo 3Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 modelsLMArena leaderboard datasetallenai/Olmo-3.1-32B-Think model cardEuroEval leaderboards (results collection), English generative leaderboard
260DeepSeek R1 Distill Llama 70B · 2-bit DeepSeek58±1local~30GB131kllama.cpp › Epoch AI — internal evaluationsMicrosoft — Phi-4-reasoning Technical Reportdeepseek-ai/DeepSeek-R1 model cardCodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)BRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)Judgemark v2 results (EQ-Bench)+1
261Phi-4-reasoning 14B · 8-bit Microsoft58±1local~21GB33kOllama › Microsoft — Phi-4-reasoning Technical Reportmicrosoft/Phi-4-reasoning model cardMedmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 modelsEuroEval leaderboards (results collection), English generative leaderboardOpen Portuguese LLM Leaderboard (archived)
262Olmo 3 32B Think · 4-bit Ai258±1local~22GB66kOllama › Olmo 3Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 modelsLMArena leaderboard datasetallenai/Olmo-3.1-32B-Think model card
263Magistral Small 1.2 · 4-bit Mistral58±1local~17GB131kllama.cpp › mistralai/Magistral-Small-2509 model cardEpoch AI — internal evaluationsApriel-1.5-15b-Thinker (arXiv:2510.01141v1), Table 4 multimodal benchmarksmistralai/Mistral-Small-4-119B-2603 model cardInception Arabic/Hindi leaderboards (AraGen-v3, HindiGen-v1, Arabic IFEval)EuroEval leaderboards (results collection), English generative leaderboard
264Nemotron-Cascade-8B-Thinking · 8-bit NVIDIA58±2†local~11GBllama.cpp › NVIDIA — Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
265Qwen3-VL 30B-A3B Instruct · 4-bit Alibaba58±1†local~23GB256kOllama › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)
266Qwen3-VL 8B Thinking · 8-bit Alibaba58±1local~12GB256kOllama › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)allenai/Olmo-3-7B-Think model cardChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)
267Qwen3 32B · 4-bit Alibaba58±0local~23GB131kOllama › Qwen/Qwen3-Next-80B-A3B-Thinking model cardQwen/Qwen3-Next-80B-A3B-Instruct model cardFalcon-H1R: Pushing the Reasoning Frontiers with a Hybrid Model for Efficient Test-Time ScalingByteDance-Seed/Seed-OSS-36B-Instruct model cardEpoch AI — internal evaluationsAider polyglot benchmark runs+17
268Qwen3 Coder 30B-A3B Instruct · 4-bit Alibaba58±1local~21GB160kOllama › Qwen/Qwen3-Coder-30B-A3B-Instruct model cardKwaipilot/KAT-Coder-V2.5-Dev model cardRoblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau Leetcode
269Nova 2 Lite Amazon58±2api $0.94/M1Mdocs.aws.amazon.com ↗Daekeun Kim Korean LLM benchmark runsLMArena leaderboard datasetBerkeley Function Calling Leaderboard result archiveAmazon AGI — τ²-Bench-VerifiedVectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
270Llama 3.3 Nemotron Super 49B v1.5 · 2-bit NVIDIA58±1local~18GB131kllama.cpp › NVIDIA — Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning ModelsLMArena leaderboard dataset
271Nemotron 3 Nano 30B-A3B · 4-bit NVIDIA58±1local~25GB262kllama.cpp › NVIDIA — Nemotron-Cascade 2 technical reportMedmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 modelsNVIDIA vendor-reported benchmark scores for its own Nemotron models (Hugging Face model cards)EuroEval leaderboards (results collection), English generative leaderboardLMArena leaderboard datasetSpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)+3
272Ministral 3 14B Reasoning 2512 · 4-bit Mistral58±1local~10GB262kllama.cpp › mistralai/Ministral-3-8B-Reasoning-2512 model cardmistralai/Ministral-3-3B-Reasoning-2512 model cardMedmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 modelsJetBrains/Mellum2-12B-A2.5B-Thinking model cardEuroEval leaderboards (results collection), English generative leaderboardSurgiQ: A Large-Scale Multi-Domain Benchmark for Evaluating Surgical Understanding in Large Language Models (arXiv:2606.08071v1)
273GPT-4o (2024-08-06) OpenAI57±1api $4.38/M128kdevelopers.openai.com ↗WildEval ZeroEval published resultsEpoch AI — internal evaluationsVector Institute Evaluation Leaderboard (Inspect Evals runs)LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsOpenAI simple-evals README benchmark results (OpenAI's own models)Aider polyglot benchmark runs+23
275DeepSeek R1 0528 Qwen3 8B · 8-bit DeepSeek57±1local~12GB128kOllama › Falcon-H1R: Pushing the Reasoning Frontiers with a Hybrid Model for Efficient Test-Time Scalingdeepseek-ai/DeepSeek-R1-0528-Qwen3-8B model cardEpoch AI — internal evaluationsBRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)EuroEval leaderboards (results collection), English generative leaderboard
276Granite 4.2 3B · 8-bit IBM57±1local~5.6GB131kllama.cpp › openbmb/MiniCPM5-2B model cardibm-granite/granite-4.2-30b model cardLMArena leaderboard dataset
277Command A (03-2025) Cohere57±1api $4.38/M +local~37GB256kazure.microsoft.com ↗Cohere — Command A technical reportLMArena leaderboard datasetBerkeley Function Calling Leaderboard result archiveFinance Agent Benchmark (Vals AI, arXiv:2508.00828v1)Open Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
278GPT-4o (2024-11-20) OpenAI57±1api $4.38/M128kdevelopers.openai.com ↗Epoch AI — internal evaluationsOpenAI simple-evals README benchmark results (OpenAI's own models)Qwen/Qwen3-235B-A22B-Instruct-2507 model cardAider polyglot benchmark runsQwen/Qwen3-30B-A3B-Instruct-2507 model cardMUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool use (arXiv:2508.18669v1)+7
279Gemini 2.5 Flash-Lite Google57±2api $0.17/M1Mai.google.dev ↗Google DeepMind Gemini model page and model cards (lab-reported scores)Berkeley Function Calling Leaderboard result archiveQwen/Qwen3.5-4B model cardMiðeind Icelandic LLM LeaderboardGalileo Agent Leaderboard (v1 and v2 results)Open Portuguese LLM Leaderboard (archived)+1
281Qwen2.5-Omni 7B · 8-bit Alibaba57±2local~10GBllama.cpp › AHELM: A Holistic Evaluation of Audio-Language Models (Stanford CRFM, arXiv:2508.21376v2)
282GPT-4o (2024-05-13) OpenAI57±0api $7.50/M128kdevelopers.openai.com ↗WildEval ZeroEval published resultsEpoch AI — internal evaluationsLiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsAlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)OpenAI simple-evals README benchmark results (OpenAI's own models)Daekeun Kim Korean LLM benchmark runs+19
283QED-Nano · 16-bit LM Provers57±2local~9.9GB262khow to run › MathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasets
284Llama 4 Maverick (402B-A17B) Meta57±1api $0.42/M~65GB1Mdocs.aws.amazon.com ↗Epoch AI — internal evaluationsAider polyglot benchmark runsLMArena leaderboard datasetArena-Hard-Auto v2.0-Preview leaderboard (repository README)Korean Canonical Legal Benchmark: Toward Knowledge-Independent Evaluation of LLMs’ Legal Reasoning CapabilitiesApriel-1.5-15b-Thinker (arXiv:2510.01141v1), Table 4 multimodal benchmarks+14
286Qwen2.5 Coder 32B Instruct · 4-bit Alibaba57±1local~23GB131kOllama › EvalPlus / EvalPerf published evaluation runsQwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)LiveCodeBench official website results (2024-12-26)Aider polyglot benchmark runsAider code editing benchmark runs (old edit leaderboard)Roblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau Leetcode+5
287Qwen3 4B Thinking 2507 · 8-bit Alibaba57±1local~7.1GB262kOllama › Qwen/Qwen3-4B-Thinking-2507 model cardMathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasetsMedmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 modelsBRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)Qwen/Qwen3.5-0.8B model cardKnowledge Index of Noah's Ark (arXiv:2606.05104v2)+2
290Athene-V2-Chat 72B · 4-bit Nexusflow56±2local (slow)~48GB33kOllama › Arena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)Arena-Hard-Auto v2.0-Preview leaderboard (repository README)LMArena leaderboard datasetBRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)
292Sky-T1 32B Preview · 4-bit NovaSky (UC Berkeley)56±5local~22GBllama.cpp › EuroEval leaderboards (results collection), English generative leaderboardBerkeley Function Calling Leaderboard result archive
293Qwen Plus (2025-01-25) Alibaba56±1api $0.60/M131kwww.alibabacloud.com ↗Epoch AI — internal evaluationsLMArena leaderboard dataset
295Qwen3-VL 4B Thinking · 8-bit Alibaba56±1local~6.9GB256kOllama › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)BEAR-Bench: A Bilingual Enterprise and Academic Reasoning Benchmark for Multimodal Models (arXiv:2608.17895v1)
296EXAONE Deep 32B · 4-bit LG AI Research56±2†local~22GB33kllama.cpp › LG AI Research vendor-reported benchmark scores for its own EXAONE models (Hugging Face model cards)
297DeepSeek R1 Distill Qwen 32B · 4-bit DeepSeek56±1local~23GB131kOllama › open-thoughts/OpenThinker2-32B model carddeepseek-ai/DeepSeek-R1 model cardopen-thoughts/OpenThinker-32B model cardEpoch AI — internal evaluationsWebApp1K models leaderboard (onekq-ai)CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)+5
298Qwen2.5-VL 72B Instruct · 4-bit Alibaba56±1local (slow)~48GB33kOllama › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)Qwen2.5-VL-32B-Instruct model cardLMArena leaderboard datasetChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era (arXiv:2503.12329v1)Kaleidoscope: In-language Exams for Massively Multilingual Vision Evaluation (arXiv:2504.07072v2)+3
299Granite 4.1 30B · 4-bit IBM56±1†local~19GBOllama › ibm-granite/granite-4.1-8b model card
300Mistral Small 3.2 24B · 8-bit Mistral56±1local~28GB128kllama.cpp › mistralai/Mistral-Small-3.2-24B-Instruct-2506 model cardEpoch AI — internal evaluationsLMArena leaderboard datasetmistralai/Mistral-Small-4-119B-2603 model cardEQ-Bench 3 canonical leaderboard resultsSpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)+4
302Qwen3 8B · 8-bit Alibaba56±1local~12GB33kOllama › Falcon-H1R: Pushing the Reasoning Frontiers with a Hybrid Model for Efficient Test-Time ScalingQwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)Epoch AI — internal evaluationsMUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool use (arXiv:2508.18669v1)allenai/Olmo-3-7B-Think model cardSynthesize and Reward: Reinforcement Learning for Multi-Step Tool Use in Live Environments (arXiv:2606.03892v2)+14
303DeepSeek R1 Distill Qwen 14B · 8-bit DeepSeek56±1local~21GB131kOllama › Epoch AI — internal evaluationsdeepseek-ai/DeepSeek-R1 model cardCodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)BRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)SurgiQ: A Large-Scale Multi-Domain Benchmark for Evaluating Surgical Understanding in Large Language Models (arXiv:2606.08071v1)EuroEval leaderboards (results collection), English generative leaderboard+2
304Ministral 3 14B · 8-bit Mistral56±1local~20GB262kOllama › JetBrains/Mellum2-12B-A2.5B-Instruct model cardMedmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 modelsEuroEval leaderboards (results collection), English generative leaderboardmistralai/Ministral-3-14B-Instruct-2512 model cardContractBench: Can LLM Agents Preserve Observation Contracts? (arXiv:2605.17281v2)mistralai/Ministral-3-8B-Instruct-2512 model card+1
305Nemotron Nano 9B v2 · 8-bit NVIDIA56±1local~13GB131kllama.cpp › Olmo 3NVIDIA — Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning ModelsNVIDIA vendor-reported benchmark scores for its own Nemotron models (Hugging Face model cards)allenai/Olmo-3-7B-Think model cardEuroEval leaderboards (results collection), English generative leaderboard
307GPT-4 Turbo (2024-04-09) OpenAI55±0api $15.00/M128kdevelopers.openai.com ↗WildEval ZeroEval published resultsEvalPlus / EvalPerf published evaluation runsEpoch AI — internal evaluationsAlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsOpenAI simple-evals README benchmark results (OpenAI's own models)+18
308Yi-Lightning 01.AI55±1api price unknown16kplatform.lingyiwanwu.com ↗Arena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)Aider polyglot benchmark runsAider code editing benchmark runs (old edit leaderboard)LMArena leaderboard dataset
309Qwen2.5 72B Instruct · 2-bit Alibaba55±1local~30GB33kllama.cpp › WildEval ZeroEval published resultsCohere — Command A technical reportEpoch AI — internal evaluationsMicrosoft Research — Phi-4 Technical Report2 OLMo 2 Furious (Team OLMo, Ai2) — authors' own evaluations of OLMo 2 Instruct and peer instruct modelsLiveCodeBench official website results (2024-12-26)+24
311Ministral 3 8B Reasoning 2512 · 4-bit Mistral55±1local~7GB262kllama.cpp › mistralai/Ministral-3-8B-Reasoning-2512 model cardmistralai/Ministral-3-3B-Reasoning-2512 model cardMedmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 modelsSurgiQ: A Large-Scale Multi-Domain Benchmark for Evaluating Surgical Understanding in Large Language Models (arXiv:2606.08071v1)
312Magistral Small 1.0 (2506) · 8-bit Mistral55±1local~28GB128kllama.cpp › mistralai/Magistral-Small-2509 model cardEpoch AI — internal evaluationsBRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)Galileo Agent Leaderboard (v1 and v2 results)
313Qwen3 30B-A3B (Apr 2025, hybrid) · 4-bit Alibaba55±1local~21GB33kOllama › Qwen/Qwen3-4B-Instruct-2507 model cardQwen/Qwen3-30B-A3B-Thinking-2507 model cardQwen/Qwen3-4B-Thinking-2507 model cardQwen/Qwen3-30B-A3B-Instruct-2507 model cardEpoch AI — internal evaluationsArena-Hard-Auto v2.0-Preview leaderboard (repository README)+10
314Molmo 2 8B · 8-bit Ai255±2local~11GBllama.cpp › Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding (Ai2, arXiv 2601.10611v4)LMArena leaderboard dataset
317Qwen3 4B Instruct 2507 · 8-bit Alibaba55±1local~7.1GB262kOllama › Qwen/Qwen3-4B-Instruct-2507 model cardMarco-MoE: Open Multilingual Mixture-of-Expert Language Models with Efficient UpcyclingQwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)Epoch AI — internal evaluationsRoblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau LeetcodeSynthesize and Reward: Reinforcement Learning for Multi-Step Tool Use in Live Environments (arXiv:2606.03892v2)+4
318Qwen2.5 Coder 14B Instruct · 8-bit Alibaba55±1local~21GB131kOllama › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)Aider code editing benchmark runs (old edit leaderboard)CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)DSEffi-Bench: Demystifying Large Language Models' Capability in Efficient Data Science Code Generation — authors' own model runsOpen Portuguese LLM Leaderboard (archived)
319Qwen3-VL 8B Instruct · 8-bit Alibaba55±1local~12GB256kOllama › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)allenai/Olmo-3-7B-Instruct model cardChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)BEAR-Bench: A Bilingual Enterprise and Academic Reasoning Benchmark for Multimodal Models (arXiv:2608.17895v1)How Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings (arXiv:2605.07492v2)
320Spark-X2.5 1.7B · 16-bit iFLYTEK (SparkLLM)55±1†local~5.1GB1MOllama › XHToken/Spark-X2.5-4B model card
322Llama 3.1 405B Instruct Meta55±1api $2.40/M~160GB128kdocs.aws.amazon.com ↗WildEval ZeroEval published resultsCohere — Command A technical reportEpoch AI — internal evaluationsLiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsLiveCodeBench official website results (2024-12-26)Arena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)+13
323Qwen2.5 32B Instruct · 4-bit Alibaba55±1local~23GB131kOllama › WildEval ZeroEval published resultsEpoch AI — internal evaluations2 OLMo 2 Furious (Team OLMo, Ai2) — authors' own evaluations of OLMo 2 Instruct and peer instruct modelsLiveCodeBench official website results (2024-12-26)Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 modelsCodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)+11
324Command A Reasoning (08-2025) · 2-bit Cohere55±2local (slow)~34GBllama.cpp › Cohere vendor-reported benchmark scores for its own models (cohere.com blog)Berkeley Function Calling Leaderboard result archive
325Bielik 11B v3.0 Instruct · 16-bit SpeakLeash55±2local~25GBhow to run › Reassessing High-Performing LLMs on Polish Medical Exams: True Competence or Bias-Driven Performance? (arXiv:2606.12250v1)SpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)SpeakLeash Polish EQ-Bench leaderboardEuroEval leaderboards (results collection), English generative leaderboard
326Olmo 3.1 32B Instruct · 4-bit Ai255±2local~22GB66kOllama › Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 modelsLMArena leaderboard datasetEuroEval leaderboards (results collection), English generative leaderboard
327OpenThinker 32B · 4-bit Open Thoughts55±1†local~23GB33kOllama › open-thoughts/OpenThinker2-32B model cardopen-thoughts/OpenThinker-32B model card
328Magistral Small 1.1 (2507) · 8-bit Mistral55±2†local~28GB40kllama.cpp › mistralai/Magistral-Small-2509 model card
329EXAONE Deep 7.8B · 4-bit LG AI Research55±2†local~6.5GB33kOllama › LG AI Research vendor-reported benchmark scores for its own EXAONE models (Hugging Face model cards)
330Qwen2.5-Math 72B Instruct · 4-bit Alibaba55±2†local (slow)~51GB4kllama.cpp › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)
331OpenThinker2 32B · 4-bit Open Thoughts54±1local~22GB33kllama.cpp › open-thoughts/OpenThinker2-32B model cardArena-Hard-Auto v2.0-Preview leaderboard (repository README)
332Falcon-H1 34B Instruct · 4-bit TII54±3local~23GB262kllama.cpp › Inception Arabic/Hindi leaderboards (AraGen-v3, HindiGen-v1, Arabic IFEval)Open Portuguese LLM Leaderboard (archived)
333Llama 3.3 70B Instruct · 2-bit Meta54±1local~24GB128kllama.cpp › Cohere — Command A technical reportEpoch AI — internal evaluationsMicrosoft Research — Phi-4 Technical Report2 OLMo 2 Furious (Team OLMo, Ai2) — authors' own evaluations of OLMo 2 Instruct and peer instruct modelsLiveCodeBench official website results (2024-12-26)Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 models+21
334Llama 4 Scout (109B-A17B) Meta54±1api $0.15/M +local~36GB328kdeepinfra.com ↗Epoch AI — internal evaluationsLMArena leaderboard datasetBerkeley Function Calling Leaderboard result archiveEQ-Bench 3 canonical leaderboard resultsSpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)BRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)+8
335Nemotron 3 Nano 4B · 8-bit NVIDIA54±1local~7GB262kOllama › openbmb/MiniCPM5-2B model cardNVIDIA vendor-reported benchmark scores for its own Nemotron models (Hugging Face model cards)
336Granite 4.1 8B · 8-bit IBM54±1local~11GB131kllama.cpp › ibm-granite/granite-4.1-8b model cardLMArena leaderboard datasetSynthesize and Reward: Reinforcement Learning for Multi-Step Tool Use in Live Environments (arXiv:2606.03892v2)
337Pixtral Large (2411) · 2-bit Mistral54±3local (slow)~51GBllama.cpp › Mistral AI vendor-reported benchmark scores for its own models (Hugging Face model cards)LMArena leaderboard dataset
338Bielik 11B v2.6 Instruct · 16-bit SpeakLeash54±3local~25GBhow to run › SpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)SpeakLeash Polish EQ-Bench leaderboardEuroEval leaderboards (results collection), English generative leaderboard
339Nova Premier Amazon54±2†api $5.00/M1Maws.amazon.com ↗Amazon vendor-reported benchmark scores for its own Nova models (Amazon Science technical reports)MASSIVE-Agents — Kulkarni et al. (2025)
340Mellum2 12B-A2.5B Thinking · 16-bit JetBrains54±1†local~27GB131khow to run › JetBrains/Mellum2.1-12B-A2.5B-Thinking model cardJetBrains/Mellum2-12B-A2.5B-Thinking model card
341Mistral Large 2 (2407) · 2-bit Mistral54±1local (slow)~45GB128kllama.cpp › WildEval ZeroEval published resultsVector Institute Evaluation Leaderboard (Inspect Evals runs)Epoch AI — internal evaluationsLiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsJamba-1.5: Hybrid Transformer-Mamba Models at Scale (AI21, arXiv 2408.12570v1)Arena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)+10
342Mistral Small 3.1 24B (2503) · 8-bit Mistral54±1local~28GB128kllama.cpp › Epoch AI — internal evaluationsmistralai/Mistral-Small-3.2-24B-Instruct-2506 model cardLMArena leaderboard datasetMistral AI vendor-reported benchmark scores for its own models (Hugging Face model cards)SpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)EQ-Bench 3 canonical leaderboard results+7
346Llama 3.1 Tulu 3 70B · 4-bit Ai254±1local (slow)~46GB131kllama.cpp › Tülu 3: Pushing Frontiers in Open Language Model Post-Training (Lambert et al., Ai2)LMArena leaderboard dataset
349GLM-4 9B Chat 1M · 16-bit Zhipu AI (THUDM)53±5local~21GB1Mhow to run › NVIDIA RULER repository README results tableOpen Portuguese LLM Leaderboard (archived)
350Mistral Small 3 24B (2501) · 8-bit Mistral53±1local~28GB32kllama.cpp › Epoch AI — internal evaluationsInception Arabic/Hindi leaderboards (AraGen-v3, HindiGen-v1, Arabic IFEval)LMArena leaderboard datasetSpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)EQ-Bench 3 canonical leaderboard resultsBRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)+6
351Qwen2-VL 72B Instruct · 4-bit Alibaba53±1local (slow)~53GBllama.cpp › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)Qwen2.5-VL-32B-Instruct model cardPixtral 12B (Mistral AI, arXiv 2410.07073v2)LMArena leaderboard datasetCapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era (arXiv:2503.12329v1)Ai2 Molmo-72B-0924 model card: Human Preference Elo Rating column
353GPT-4o mini (2024-07-18) OpenAI53±0api $0.26/M128kdevelopers.openai.com ↗EvalPlus / EvalPerf published evaluation runsWildEval ZeroEval published resultsmicrosoft/Phi-4-mini-instruct model cardVector Institute Evaluation Leaderboard (Inspect Evals runs)Epoch AI — internal evaluationsAlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)+32
355Llama 3.1 Tulu 3 70B DPO · 2-bit Ai253±1local~22GB131kllama.cpp › Epoch AI — internal evaluationsTülu 3: Pushing Frontiers in Open Language Model Post-Training (Lambert et al., Ai2)
357Qwen2.5-VL 32B Instruct · 4-bit Alibaba53±2local~23GB33kOllama › Qwen2.5-VL-32B-Instruct model cardApriel-1.5-15b-Thinker (arXiv:2510.01141v1), Table 4 multimodal benchmarksLMArena leaderboard datasetChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)Kaleidoscope: In-language Exams for Massively Multilingual Vision Evaluation (arXiv:2504.07072v2)VMMU: A Vietnamese Multitask Multimodal Understanding and Reasoning Benchmark (arXiv:2508.13680v5)+1
359s1.1 32B · 4-bit Simple Scaling53±1local~22GB33kllama.cpp › open-thoughts/OpenThinker2-32B model cardopen-thoughts/OpenThinker-32B model cardArena-Hard-Auto v2.0-Preview leaderboard (repository README)
361Olmo 3 7B Think · 8-bit Ai253±1local~11GB66kOllama › Olmo 3Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 modelsallenai/Olmo-3-7B-Think model cardJetBrains/Mellum2-12B-A2.5B-Thinking model cardEuroEval leaderboards (results collection), English generative leaderboard
362GPT-4.1 nano OpenAI53±1api $0.17/M1Mdevelopers.openai.com ↗OpenAI simple-evals README benchmark results (OpenAI's own models)Epoch AI — internal evaluationsDaekeun Kim Korean LLM benchmark runsOpenAI vendor-reported benchmark scores for its own models (openai.com announcement posts and Deployment Safety Hub system cards)LMArena leaderboard datasetAider polyglot benchmark runs+11
364Gemma 3 27B · 4-bit Google53±1local~19GB131kOllama › Gemma Team — Gemma 4 Technical ReportGoogle DeepMind Gemma 3 270M IT model cardEpoch AI — internal evaluations2 OLMo 2 Furious (Team OLMo, Ai2) — authors' own evaluations of OLMo 2 Instruct and peer instruct modelsMedmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 modelsLMArena leaderboard dataset+23
365Phi-4 14B · 8-bit Microsoft53±1local~21GB16kOllama › Epoch AI — internal evaluationsMicrosoft Research — Phi-4 Technical ReportMicrosoft — Phi-4-reasoning Technical ReportDaekeun Kim Korean LLM benchmark runsmicrosoft/phi-4 model cardmicrosoft/Phi-4-reasoning model card+11
366Gemma 4 E4B · 8-bit Google53±1local~9.9GB131kllama.cpp › Gemma Team — Gemma 4 Technical Reportopenbmb/MiniCPM5-2B model cardJetBrains/Mellum2.1-12B-A2.5B-Thinking model cardXHToken/Spark-X2.5-4B model cardLiquidAI/LFM2.5-2.6B model cardEuroEval leaderboards (results collection), English generative leaderboard+7
367Ministral 3 8B · 8-bit Mistral53±1local~13GB262kOllama › Marco-MoE: Open Multilingual Mixture-of-Expert Language Models with Efficient UpcyclingMedmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 modelsEuroEval leaderboards (results collection), English generative leaderboardmistralai/Ministral-3-14B-Instruct-2512 model cardContractBench: Can LLM Agents Preserve Observation Contracts? (arXiv:2605.17281v2)mistralai/Ministral-3-8B-Instruct-2512 model card+2
368Qwen3-VL 4B Instruct · 8-bit Alibaba53±1local~6.9GB256kOllama › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)How Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings (arXiv:2605.07492v2)
370LFM2.5 2.6B · 8-bit Liquid AI53±1local~4.5GB131kllama.cpp › openbmb/MiniCPM5-2B model cardLiquidAI/LFM2.5-2.6B model card
371Bielik 11B v2.1 Instruct · 16-bit SpeakLeash53±3local~25GBhow to run › SpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)SpeakLeash Polish EQ-Bench leaderboardOpen Portuguese LLM Leaderboard (archived)
372Llama 3.1 70B Instruct · 2-bit Meta52±1local~27GB128kllama.cpp › WildEval ZeroEval published resultsVector Institute Evaluation Leaderboard (Inspect Evals runs)2 OLMo 2 Furious (Team OLMo, Ai2) — authors' own evaluations of OLMo 2 Instruct and peer instruct modelsLiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsEpoch AI — internal evaluationsArena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)+22
374Qwen2.5-Math 7B Instruct · 4-bit Alibaba52±2†local~6.4GB4kllama.cpp › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)
375LFM2.5 8B-A1B · 8-bit Liquid AI52±1local~13GB128kOllama › openbmb/MiniCPM5-2B model cardLiquidAI/LFM2.5-8B-A1B model card
379Bielik 11B v2.2 Instruct · 16-bit SpeakLeash52±3local~25GBhow to run › SpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)SpeakLeash Polish EQ-Bench leaderboardOpen Portuguese LLM Leaderboard (archived)
380Granite 4.0 H Small (32B-A9B) · 4-bit IBM52±1local~22GB131kOllama › ibm-granite/granite-4.0-h-small model cardMarco-MoE: Open Multilingual Mixture-of-Expert Language Models with Efficient UpcyclingMedmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 modelsLMArena leaderboard datasetEuroEval leaderboards (results collection), English generative leaderboardDiagnosticIQ: A Benchmark for LLM-Based Industrial Maintenance Action Recommendation from Symbolic Rules (arXiv:2605.08614v1)+1
381Llama 3.1 Nemotron 70B Instruct · 4-bit NVIDIA52±1local (slow)~46GB128kllama.cpp › Tülu 3: Pushing Frontiers in Open Language Model Post-Training (Lambert et al., Ai2)Arena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)Aider code editing benchmark runs (old edit leaderboard)Arena-Hard-Auto v2.0-Preview leaderboard (repository README)LMArena leaderboard datasetLiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasets+4
384Aya Expanse 32B · 4-bit Cohere52±2local~22GB128kOllama › LMArena leaderboard datasetInception Arabic/Hindi leaderboards (AraGen-v3, HindiGen-v1, Arabic IFEval)Korean Canonical Legal Benchmark: Toward Knowledge-Independent Evaluation of LLMs’ Legal Reasoning CapabilitiesOpen Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)EuroEval leaderboards (results collection), English generative leaderboardOpen Portuguese LLM Leaderboard (archived)+1
385Gemma 3 12B · 8-bit Google52±1local~17GB131kOllama › Google DeepMind Gemma 3 270M IT model cardMarco-MoE: Open Multilingual Mixture-of-Expert Language Models with Efficient UpcyclingMedmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 modelsGemma Team — Gemma 3 Technical ReportEpoch AI — internal evaluationsMIMIC Clinical Decision Making leaderboard+10
386Qwen2.5 Coder 7B Instruct · 8-bit Alibaba52±1local~12GB131kOllama › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)LiveCodeBench official website results (2024-12-26)Aider code editing benchmark runs (old edit leaderboard)CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)Open Portuguese LLM Leaderboard (archived)
387Qwen2.5 14B Instruct · 8-bit Alibaba52±1local~21GB131kOllama › 2 OLMo 2 Furious (Team OLMo, Ai2) — authors' own evaluations of OLMo 2 Instruct and peer instruct modelsMicrosoft Research — Phi-4 Technical Reportmicrosoft/phi-4 model cardReinforcing Real-world Service Agents: InteractCS-RL (arXiv:2602.22697v1)CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)SpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)+7
388Cogito v1 Preview Llama 8B · 8-bit Deep Cogito51±5local~12GB128kOllama › EuroEval leaderboards (results collection), English generative leaderboardOpen Portuguese LLM Leaderboard (archived)
390GPT-4 (0613) OpenAI51±1api $37.50/M8kdevelopers.openai.com ↗Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsAlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsEpoch AI — internal evaluationsTulu 2 — base and instruction-tuned evaluationsArena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)+9
391OpenCoder-8B-Instruct · 16-bit INF (infly)51±1local~18GBhow to run › EvalPlus / EvalPerf published evaluation runsEuroEval leaderboards (results collection), English generative leaderboard
392Command A Translate (08-2025) Cohere51±5†api price unknown8kdocs.cohere.com ↗Cohere — North Small Translate (arXiv:2609.13916v1)
393Llama 3.1 Nemotron 51B Instruct · 4-bit NVIDIA51±2local (slow)~34GBllama.cpp › Puzzle: Distillation-Based NAS for Inference-Optimized LLMs (arXiv:2411.19146v5)LMArena leaderboard dataset
394Ministral 3 3B Reasoning 2512 · 4-bit Mistral51±1local~3.8GB262kllama.cpp › mistralai/Ministral-3-8B-Reasoning-2512 model cardmistralai/Ministral-3-3B-Reasoning-2512 model cardMedmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 modelsEuroEval leaderboards (results collection), English generative leaderboard
395Qwen3 4B · 8-bit Alibaba51±1local~7.1GB33kOllama › Qwen/Qwen3-4B-Thinking-2507 model cardQwen/Qwen3-4B-Instruct-2507 model cardLFM2 Technical Report — Liquid AI own SmolLM3 evaluationHuggingFaceTB/SmolLM3-3B model card (Evaluation section)Epoch AI — internal evaluationsArena-Hard-Auto v2.0-Preview leaderboard (repository README)+8
397Llama-3-Instruct-8B-SimPO-ExPO · 16-bit Chujie Zheng (ExPO)51±1local~18GBhow to run › AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)WildBench v2 leaderboard data (Ai2)Open Portuguese LLM Leaderboard (archived)
398LFM2 24B-A2B · 8-bit Liquid AI51±1local~28GB33kllama.cpp › Marco-MoE: Open Multilingual Mixture-of-Expert Language Models with Efficient Upcycling
399AceReason-Nemotron-1.0-14B · 8-bit NVIDIA51±2†local~18GBllama.cpp › NVIDIA — Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
400Llama-3-Instruct-8B-SimPO · 16-bit Princeton NLP51±1local~18GBhow to run › AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)WildBench v2 leaderboard data (Ai2)Open Portuguese LLM Leaderboard (archived)
401Athene-70B · 2-bit Nexusflow51±1local~29GBllama.cpp › WildEval ZeroEval published resultsArena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)WildBench v2 leaderboard data (Ai2)LMArena leaderboard dataset
402Qwen2 72B Instruct · 4-bit Alibaba51±1local (slow)~48GB131kOllama › WildEval ZeroEval published resultsLiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsAlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Epoch AI — internal evaluationsArena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)BigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4+14
403Bielik 11B v2.0 Instruct · 16-bit SpeakLeash51±3local~25GBhow to run › SpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)SpeakLeash Polish EQ-Bench leaderboardOpen Portuguese LLM Leaderboard (archived)
404OpenThinker3 7B · 16-bit Open Thoughts50±1local~21GB33khow to run › Olmo 3allenai/Olmo-3-7B-Think model cardBRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)
405CodeQwen1.5 7B Chat · 8-bit Alibaba50±1local~11GB64kOllama › EvalPlus / EvalPerf published evaluation runsQwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)BigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4
408Llama-3-8B-ProLong-512k-Instruct · 4-bit Princeton NLP50±5local (slow)~35GBhow to run › NVIDIA RULER repository README results tableOpen Portuguese LLM Leaderboard (archived)
409EXAONE Deep 2.4B · 4-bit LG AI Research50±2†local~3.2GB33kllama.cpp › LG AI Research vendor-reported benchmark scores for its own EXAONE models (Hugging Face model cards)
410Mellum2 12B-A2.5B Instruct · 16-bit JetBrains50±2†local~27GB131khow to run › JetBrains/Mellum2-12B-A2.5B-Instruct model card
411OpenCodeInterpreter-DS-33B · 4-bit M-A-P50±1local~22GBllama.cpp › EvalPlus / EvalPerf published evaluation runs
413DeepSeek-Coder 33B Instruct · 4-bit DeepSeek50±1local~23GB16kOllama › EvalPlus / EvalPerf published evaluation runsTop Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4LiveCodeBench official website results (2024-12-26)CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)CRUXEval published evaluation results (authors' generations and scores)+1
414Yi 34B 200K (base) · 4-bit 01.AI50±5local~23GB200kllama.cpp › NVIDIA RULER repository README results tableOpen Portuguese LLM Leaderboard (archived)
415Gemma 2 27B IT · 4-bit Google50±1local~19GB8kOllama › WildEval ZeroEval published results2 OLMo 2 Furious (Team OLMo, Ai2) — authors' own evaluations of OLMo 2 Instruct and peer instruct modelsLiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsEpoch AI — internal evaluationsArena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)WildBench v2 leaderboard data (Ai2)+10
416Bielik 11B v2.3 Instruct · 8-bit SpeakLeash50±2local~14GBllama.cpp › SpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)Berkeley Function Calling Leaderboard result archiveSpeakLeash Polish EQ-Bench leaderboardOpen Portuguese LLM Leaderboard (archived)EuroEval leaderboards (results collection), English generative leaderboard
417Qwen2.5-VL 7B Instruct · 8-bit Alibaba50±1local~11GBOllama › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)
419Codestral 22B v0.1 · 8-bit Mistral AI50±1local~30GB32kOllama › EvalPlus / EvalPerf published evaluation runsAider code editing benchmark runs (old edit leaderboard)DSEffi-Bench: Demystifying Large Language Models' Capability in Efficient Data Science Code Generation — authors' own model runsOpen Portuguese LLM Leaderboard (archived)
421Llama 3 70B Instruct · 2-bit Meta50±0local~24GB8kllama.cpp › EvalPlus / EvalPerf published evaluation runsWildEval ZeroEval published resultsGranite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsLiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsAlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Epoch AI — internal evaluations+17
423Nova Pro Amazon50±1api $1.40/M300kdocs.aws.amazon.com ↗Amazon vendor-reported benchmark scores for its own Nova models (Amazon Science technical reports)Aider code editing benchmark runs (old edit leaderboard)LMArena leaderboard datasetBerkeley Function Calling Leaderboard result archiveGalileo Agent Leaderboard (v1 and v2 results)Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
424WizardCoder 33B V1.1 · 4-bit WizardLM50±1local~23GB16kOllama › EvalPlus / EvalPerf published evaluation runsTop Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsWizardLM team vendor-reported scores for its own WizardCoder models (Hugging Face card)
425Mistral Small Instruct 22B (2409) · 8-bit Mistral AI49±2local~30GB32kOllama › CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)EvalPlus / EvalPerf published evaluation runsSpeakLeash Polish EQ-Bench leaderboardBRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)Open Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)Galileo Agent Leaderboard (v1 and v2 results)
426Qwen2-Math 72B Instruct · 4-bit Alibaba49±1local (slow)~45GB4kOllama › LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsQwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)
427OLMo 2 32B Instruct (0325) · 4-bit Ai249±1local~21GBllama.cpp › 2 OLMo 2 Furious (Team OLMo, Ai2) — authors' own evaluations of OLMo 2 Instruct and peer instruct modelsLMArena leaderboard datasetallenai/Olmo-3.1-32B-Think model cardEuroEval leaderboards (results collection), English generative leaderboardOpen Portuguese LLM Leaderboard (archived)
428OpenThinker2 7B · 4-bit Open Thoughts49±2†local~6.4GB33kllama.cpp › open-thoughts/OpenThinker2-7B model card
429Aya 23 35B · 4-bit Cohere For AI49±3local~24GB8kllama.cpp › SpeakLeash Polish EQ-Bench leaderboardOpen Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)EuroEval leaderboards (results collection), English generative leaderboardOpen Portuguese LLM Leaderboard (archived)
430Granite 4.1 3B · 4-bit IBM49±1†local~3.7GBOllama › ibm-granite/granite-4.1-8b model card
431OpenCodeInterpreter-DS-6.7B · 16-bit M-A-P49±1local~16GBhow to run › EvalPlus / EvalPerf published evaluation runs
432Artigenz-Coder-DS-6.7B · 16-bit Artigenz49±1local~16GBhow to run › EvalPlus / EvalPerf published evaluation runs
433LFM2.5 1.2B Thinking · 8-bit Liquid AI49±2local~3.5GB33kOllama › LiquidAI/LFM2.5-1.2B-Thinking model cardEuroEval leaderboards (results collection), English generative leaderboard
434Qwen3-VL 2B Thinking · 8-bit Alibaba49±1local~4.2GB256kOllama › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)
435speechless-codellama-34b-v2.0 · 4-bit uukuguy49±1local~23GBllama.cpp › EvalPlus / EvalPerf published evaluation runs
436Pixtral 12B (2409) · 16-bit Mistral49±2local~28GBhow to run › Pixtral 12B (Mistral AI, arXiv 2410.07073v2)LMArena leaderboard datasetVisEditBench: Can Vision-Language Models Edit Visualization Code from Multimodal Feedback? (arXiv:2608.10408v1)Ai2 Molmo-72B-0924 model card: Human Preference Elo Rating column
437Nova Lite Amazon49±2api $0.10/M300kdocs.aws.amazon.com ↗LMArena leaderboard datasetBerkeley Function Calling Leaderboard result archiveGalileo Agent Leaderboard (v1 and v2 results)Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
438MegaBeam-Mistral-7B-512k · 16-bit AWS (aws-prototyping)49±4local~17GBhow to run › NVIDIA RULER repository README results tableOpen Portuguese LLM Leaderboard (archived)
441AceReason-Nemotron-1.1-7B · 8-bit NVIDIA49±2†local~10GBllama.cpp › NVIDIA — Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
443Yi-Coder 9B Chat · 8-bit 01.AI49±1local~13GB128kOllama › LiveCodeBench official website results (2024-12-26)Aider code editing benchmark runs (old edit leaderboard)CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)EvalPlus / EvalPerf published evaluation runsOpen Portuguese LLM Leaderboard (archived)
444Qwen2-Math 7B Instruct · 8-bit Alibaba49±2†local~10GB4kllama.cpp › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)
445Magicoder-S-DS 6.7B · 4-bit UIUC (ise-uiuc)49±1local~30GBhow to run › EvalPlus / EvalPerf published evaluation runsTop Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4CRUXEval published evaluation results (authors' generations and scores)
446InternLM2.5 7B Chat · 8-bit Shanghai AI Laboratory (InternLM)49±2local~12GBOllama › InternLM GitHub repository model cards (Shanghai AI Laboratory)Open Portuguese LLM Leaderboard (archived)
447Hermes 3 Llama 3.1 70B · 4-bit Nous Research49±1local (slow)~44GB131kOllama › Nous Research vendor-reported scores for its own Hermes models (Hermes 3 Technical Report)LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasets
448Qwen2.5 7B Instruct · 8-bit Alibaba48±1local~12GB131kOllama › microsoft/Phi-4-mini-instruct model cardWildEval ZeroEval published results2 OLMo 2 Furious (Team OLMo, Ai2) — authors' own evaluations of OLMo 2 Instruct and peer instruct modelsLiveCodeBench official website results (2024-12-26)Inception Arabic/Hindi leaderboards (AraGen-v3, HindiGen-v1, Arabic IFEval)Epoch AI — internal evaluations+12
449DeepSeek R1 Distill Qwen 7B · 8-bit DeepSeek48±1local~12GB131kOllama › open-thoughts/OpenThinker2-7B model carddeepseek-ai/DeepSeek-R1 model cardallenai/Olmo-3-7B-Think model cardMicrosoft — Phi-4-Mini Technical Reportmicrosoft/Phi-4-mini-reasoning model cardopen-thoughts/OpenThinker-7B model card+6
450XwinCoder-34B · 4-bit Xwin-LM48±1local~23GBllama.cpp › EvalPlus / EvalPerf published evaluation runs
451StarChat2 15B v0.1 · 8-bit Hugging Face48±1local~19GB16kllama.cpp › EvalPlus / EvalPerf published evaluation runs
452Code Millenials 34B · 4-bit Bud Ecosystem48±1local~23GBllama.cpp › EvalPlus / EvalPerf published evaluation runs
455T5 Large · 4-bit Google48±9local~4.6GB1khow to run › COPEN — EMNLP 2022 original zero-shot evaluations
456WaveCoder-Ultra-6.7B · 4-bit Microsoft48±1local~30GBhow to run › EvalPlus / EvalPerf published evaluation runs
457Phi-3.5-MoE-instruct · 4-bit Microsoft48±1local~28GB128kllama.cpp › LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsDaekeun Kim Korean LLM benchmark runsBRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
460Gemma 3n E4B · 8-bit Google48±1local~12GB32kOllama › Google DeepMind Gemma 3n E2B IT model cardLMArena leaderboard datasetOpen Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)EuroEval leaderboards (results collection), English generative leaderboard
461Hermes 2 Theta Llama-3 70B · 4-bit Nous Research48±2local (slow)~47GB8kllama.cpp › Epoch AI — internal evaluations
462Granite 4.0 H Tiny (7B-A1B) · 4-bit IBM48±1local~5.9GB131kllama.cpp › ibm-granite/granite-4.0-h-small model cardEuroEval leaderboards (results collection), English generative leaderboardVectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
463DeepSeek-Coder 7B Instruct v1.5 · 16-bit DeepSeek48±1local~16GBhow to run › EvalPlus / EvalPerf published evaluation runsTop Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsCodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)
464Qwen2 57B-A14B Instruct · 4-bit Alibaba48±2local (slow)~38GB33kllama.cpp › BigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4SpeakLeash Polish EQ-Bench leaderboardOpen Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)Open Portuguese LLM Leaderboard (archived)
465Qwen2.5 Coder 3B Instruct · 4-bit Alibaba48±1local~3.7GB33kllama.cpp › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)Aider code editing benchmark runs (old edit leaderboard)
466DeepSeek-Coder 6.7B Instruct · 8-bit DeepSeek48±1local~9.1GB16kOllama › EvalPlus / EvalPerf published evaluation runsTop Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4LiveCodeBench official website results (2024-12-26)CRUXEval published evaluation results (authors' generations and scores)
467MiniCPM3-4B · 4-bit OpenBMB48±2local~4.1GB32kllama.cpp › LiveCodeBench official website results (2024-12-26)Berkeley Function Calling Leaderboard result archive
468Bielik 4.5B v3.0 Instruct · 16-bit SpeakLeash48±2local~12GBhow to run › SpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)Reassessing High-Performing LLMs on Polish Medical Exams: True Competence or Bias-Driven Performance? (arXiv:2606.12250v1)SpeakLeash Polish EQ-Bench leaderboardEuroEval leaderboards (results collection), English generative leaderboard
469Qwen3.5 2B · 8-bit Alibaba47±1local~4.9GB262kOllama › Qwen/Qwen3.5-2B model cardopenbmb/MiniCPM5-2B model cardXHToken/Spark-X2.5-4B model cardCohereLabs/North-Micro-Vision-Instruct model card (benchmark table)EuroEval leaderboards (results collection), English generative leaderboardMathArena ArXivMath / BrokenArXiv / ArXivLean model-output datasets+7
470Gemma 2 9B IT · 8-bit Google47±1local~14GB8kOllama › microsoft/Phi-4-mini-instruct model cardWildEval ZeroEval published results2 OLMo 2 Furious (Team OLMo, Ai2) — authors' own evaluations of OLMo 2 Instruct and peer instruct modelsLiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsEpoch AI — internal evaluationsInternLM GitHub repository model cards (Shanghai AI Laboratory)+14
471Command R Plus (08-2024) Cohere47±1api $4.38/M~67GB128kdocs.cohere.com ↗Cohere — Command A technical reportLiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsAider code editing benchmark runs (old edit leaderboard)LMArena leaderboard datasetOpen Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)NVIDIA RULER repository README results table+1
472GLM-4 9B Chat · 8-bit Zhipu AI (Z.ai)47±2local~14GB128kOllama › WildBench v2 leaderboard data (Ai2)SpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)SpeakLeash Polish EQ-Bench leaderboardBerkeley Function Calling Leaderboard result archiveOpen Portuguese LLM Leaderboard (archived)ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools (Team GLM, arXiv 2406.12793v2)+1
473Yi-1.5 34B (base) · 4-bit 01.AI47±3local~23GB4kllama.cpp › BigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4EuroEval leaderboards (results collection), English generative leaderboardOpen Portuguese LLM Leaderboard (archived)
474Phi-4-mini-reasoning 3.8B · 8-bit Microsoft47±2local~5.8GB128kllama.cpp › microsoft/Phi-4-mini-reasoning model cardBRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)EuroEval leaderboards (results collection), English generative leaderboard
475Qwen1.5 110B Chat · 2-bit Alibaba47±1local (slow)~45GB32kllama.cpp › LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsAlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)BigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4Aider code editing benchmark runs (old edit leaderboard)Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard dataset+1
476WhiteRabbitNeo-33B-v1 · 4-bit WhiteRabbitNeo47±1local~22GBllama.cpp › EvalPlus / EvalPerf published evaluation runs
477DeepSeek R1 Distill Llama 8B · 8-bit DeepSeek47±1local~12GB131kOllama › deepseek-ai/DeepSeek-R1 model cardMicrosoft — Phi-4-Mini Technical Reportmicrosoft/Phi-4-mini-reasoning model cardCodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)BRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)EuroEval leaderboards (results collection), English generative leaderboard+1
478EXAONE 4.0 1.2B · 8-bit LG AI Research47±2†local~3.6GB66kllama.cpp › LG AI Research vendor-reported benchmark scores for its own EXAONE models (Hugging Face model cards)
480speechless-coder-ds-6.7b · 4-bit uukuguy47±1local~16GBhow to run › EvalPlus / EvalPerf published evaluation runs
481Gemma 4 E2B · 8-bit Google47±1local~6.8GB131kllama.cpp › Gemma Team — Gemma 4 Technical Reportopenbmb/MiniCPM5-2B model cardXHToken/Spark-X2.5-4B model cardCohereLabs/North-Micro-Vision-Instruct model card (benchmark table)LiquidAI/LFM2.5-2.6B model cardEuroEval leaderboards (results collection), English generative leaderboard+6
482Magicoder-S-CL-7B · 4-bit UIUC (ise-uiuc)47±1local~30GBhow to run › EvalPlus / EvalPerf published evaluation runs
483Aya Expanse 8B · 8-bit Cohere47±2local~12GB8kOllama › LMArena leaderboard datasetInception Arabic/Hindi leaderboards (AraGen-v3, HindiGen-v1, Arabic IFEval)Open Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)Open Portuguese LLM Leaderboard (archived)EuroEval leaderboards (results collection), English generative leaderboardVectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
484Phind CodeLlama 34B v2 · 4-bit Phind47±1local~23GB16kllama.cpp › EvalPlus / EvalPerf published evaluation runsTop Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsCRUXEval published evaluation results (authors' generations and scores)
486InternLM2.5 7B Chat 1M · 16-bit Shanghai AI Laboratory (InternLM)47±4local~18GBhow to run › NVIDIA RULER repository README results tableOpen Portuguese LLM Leaderboard (archived)
487EuroLLM 9B Instruct · 16-bit UTTER (EuroLLM)47±3local~21GB4khow to run › SpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)SpeakLeash Polish EQ-Bench leaderboardOpen Portuguese LLM Leaderboard (archived)EuroEval leaderboards (results collection), English generative leaderboard
488Granite 4.0 H Micro 3B · 4-bit IBM47±1local~3.5GB131kllama.cpp › ibm-granite/granite-4.0-h-small model cardEuroEval leaderboards (results collection), English generative leaderboardVectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
489GPT-3.5 Turbo (0125) OpenAI46±1api $0.75/M16kdevelopers.openai.com ↗WildEval ZeroEval published resultsTop Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runs2 OLMo 2 Furious (Team OLMo, Ai2) — authors' own evaluations of OLMo 2 Instruct and peer instruct modelsLiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsEpoch AI — internal evaluationsArena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)+11
491Jamba 1.5 Mini · 4-bit AI21 Labs46±1local (slow)~34GBllama.cpp › Jamba-1.5: Hybrid Transformer-Mamba Models at Scale (AI21, arXiv 2408.12570v1)LMArena leaderboard datasetNVIDIA RULER repository README results tableVectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
492MedGemma 4B IT · 8-bit Google46±3local~5.8GBllama.cpp › Reassessing High-Performing LLMs on Polish Medical Exams: True Competence or Bias-Driven Performance? (arXiv:2606.12250v1)BRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)Open Portuguese LLM Leaderboard (archived)SurgiQ: A Large-Scale Multi-Domain Benchmark for Evaluating Surgical Understanding in Large Language Models (arXiv:2606.08071v1)
493OLMo 2 13B Instruct (1124) · 8-bit Allen Institute for AI46±1local~19GB4kOllama › 2 OLMo 2 Furious (Team OLMo, Ai2) — authors' own evaluations of OLMo 2 Instruct and peer instruct modelsEuroEval leaderboards (results collection), English generative leaderboardVectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
494Falcon-H1 7B Instruct · 16-bit TII46±3local~17GB262khow to run › Inception Arabic/Hindi leaderboards (AraGen-v3, HindiGen-v1, Arabic IFEval)Open Portuguese LLM Leaderboard (archived)
496Cogito v1 Preview Llama 3B · 8-bit Deep Cogito46±4local~6.6GB128kOllama › EuroEval leaderboards (results collection), English generative leaderboardOpen Portuguese LLM Leaderboard (archived)
497Code Llama 70B Instruct · 2-bit Meta46±1local~28GB16kllama.cpp › EvalPlus / EvalPerf published evaluation runsTop Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsGranite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsCode Llama: Open Foundation Models for Code — authors' own runsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)+1
498Hermes 2 Pro Llama 3 8B · 4-bit Nous Research46±3local~18GB8khow to run › SpeakLeash Polish EQ-Bench leaderboardOpen Portuguese LLM Leaderboard (archived)Berkeley Function Calling Leaderboard result archive
500Granite 4.0 Micro 3B · 8-bit IBM46±1local~5.3GB131kllama.cpp › ibm-granite/granite-4.0-h-small model cardEpoch AI — internal evaluationsEuroEval leaderboards (results collection), English generative leaderboardVectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
501Command R (08-2024) · 4-bit Cohere46±1local~22GB128kOllama › LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsCohere — Command A technical reportAider code editing benchmark runs (old edit leaderboard)LMArena leaderboard datasetOpen Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)NVIDIA RULER repository README results table+3
503Nova Micro Amazon46±2api $0.061/M128kdocs.aws.amazon.com ↗LMArena leaderboard datasetMASSIVE-Agents — Kulkarni et al. (2025)Berkeley Function Calling Leaderboard result archiveGalileo Agent Leaderboard (v1 and v2 results)Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
504T5 Base · 4-bit Google46±9local~2.4GB1khow to run › COPEN — EMNLP 2022 original zero-shot evaluations
505OpenChat 3.5 0106 · 8-bit OpenChat46±1local~11GB8kOllama › EvalPlus / EvalPerf published evaluation runsTop Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsPolyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard datasetSpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)SpeakLeash Polish EQ-Bench leaderboard+1
506Qwen2-VL 7B Instruct · 8-bit Alibaba46±1local~11GBllama.cpp › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)Pixtral 12B (Mistral AI, arXiv 2410.07073v2)LMArena leaderboard datasetCapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era (arXiv:2503.12329v1)Ai2 Molmo-72B-0924 model card: Human Preference Elo Rating columnVectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
507Qwen2.5-Math 1.5B Instruct · 4-bit Alibaba46±2†local~2.5GB4kllama.cpp › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)
508Yi 1.5 34B Chat · 4-bit 01.AI46±1local~24GB4kOllama › WildEval ZeroEval published resultsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4Epoch AI — internal evaluationsWildBench v2 leaderboard data (Ai2)Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard dataset+5
510Granite 34B Code Instruct (8K) · 4-bit IBM46±1local~24GBllama.cpp › Granite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)EuroEval leaderboards (results collection), English generative leaderboard
511WizardCoder Python 34B V1.0 · 4-bit WizardLM46±1local~23GB16kllama.cpp › EvalPlus / EvalPerf published evaluation runsTop Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsWizardLM team vendor-reported scores for its own WizardCoder models (Hugging Face card)CRUXEval published evaluation results (authors' generations and scores)
515Granite 3.3 8B Instruct · 8-bit IBM46±1local~11GB128kllama.cpp › ibm-granite/granite-3.3-8b-instruct model cardallenai/Olmo-3-7B-Instruct model cardDiagnosticIQ: A Benchmark for LLM-Based Industrial Maintenance Action Recommendation from Symbolic Rules (arXiv:2605.08614v1)Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
516Tulu 2 70B · 2-bit Allen Institute for AI46±2†local~28GBllama.cpp › Tulu 2 — base and instruction-tuned evaluations
518OpenChat 3.5 0106 Gemma · 16-bit OpenChat46±3local~19GB8khow to run › SpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)SpeakLeash Polish EQ-Bench leaderboardOpen Portuguese LLM Leaderboard (archived)
519Olmo 3 7B Instruct · 8-bit Ai246±1local~11GB66kOllama › Olmo 3JetBrains/Mellum2-12B-A2.5B-Instruct model cardMedmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 modelsallenai/Olmo-3-7B-Instruct model cardEuroEval leaderboards (results collection), English generative leaderboard
520InternLM2.5 20B Chat · 8-bit Shanghai AI Laboratory (InternLM)46±2local~27GB33kOllama › Arena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)LMArena leaderboard datasetCodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)Open Portuguese LLM Leaderboard (archived)
521StarCoder2-15B-Instruct-v0.1 · 8-bit BigCode46±1local~19GB16kllama.cpp › EvalPlus / EvalPerf published evaluation runsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4
522Qwen1.5 72B Chat · 2-bit Alibaba45±1local~31GB32kllama.cpp › EvalPlus / EvalPerf published evaluation runsTop Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsLiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsAlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Arena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)BigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4+9
523speechless-starcoder2-15b · 8-bit uukuguy45±1local~19GBllama.cpp › EvalPlus / EvalPerf published evaluation runs
524Ministral 3 3B · 8-bit Mistral45±1local~6.9GB262kOllama › Marco-MoE: Open Multilingual Mixture-of-Expert Language Models with Efficient UpcyclingCohereLabs/North-Micro-Vision-Instruct model card (benchmark table)Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 modelsmistralai/Ministral-3-14B-Instruct-2512 model cardmistralai/Ministral-3-8B-Instruct-2512 model cardEuroEval leaderboards (results collection), English generative leaderboard+2
526OpenThinker 7B · 8-bit Open Thoughts45±2†local~10GB33kllama.cpp › open-thoughts/OpenThinker2-7B model cardopen-thoughts/OpenThinker-7B model card
527Phi-3 Medium 128K Instruct · 8-bit Microsoft45±1local~20GB128kOllama › LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsEpoch AI — internal evaluationsCodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)NVIDIA RULER repository README results tableOpen Portuguese LLM Leaderboard (archived)
528QwQ-32B-Preview · 4-bit Alibaba45±2local~23GB33kOllama › LMArena leaderboard datasetEvalPlus / EvalPerf published evaluation runsBRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)Open Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)Open Portuguese LLM Leaderboard (archived)Berkeley Function Calling Leaderboard result archive+2
529DeepSeek-Coder-V2 Lite Instruct (16B-A2.4B) · 8-bit DeepSeek45±1local~22GB128kOllama › LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsLiveCodeBench official website results (2024-12-26)EvalPlus / EvalPerf published evaluation runsCodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)DSEffi-Bench: Demystifying Large Language Models' Capability in Efficient Data Science Code Generation — authors' own model runsWebApp1K models leaderboard (onekq-ai)+1
533Phi-3-medium-4k-instruct · 8-bit Microsoft45±1local~20GB4kOllama › LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsArena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard datasetEvalPlus / EvalPerf published evaluation runsSpeakLeash Polish EQ-Bench leaderboard+1
534Qwen2-Math 1.5B Instruct · 8-bit Alibaba45±2†local~3.2GB4kllama.cpp › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)
536Llama 3.1 8B Instruct · 8-bit Meta45±0local~12GB128kOllama › EvalPlus / EvalPerf published evaluation runsIBM Granite 3.0 Language Models technical report (GitHub)microsoft/Phi-4-mini-instruct model cardWildEval ZeroEval published results2 OLMo 2 Furious (Team OLMo, Ai2) — authors' own evaluations of OLMo 2 Instruct and peer instruct modelsLiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasets+25
537Command R Plus (04-2024) · 2-bit Cohere45±1local (slow)~43GB128kllama.cpp › EvalPlus / EvalPerf published evaluation runsWildEval ZeroEval published resultsVector Institute Evaluation Leaderboard (Inspect Evals runs)LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsArena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)Aider code editing benchmark runs (old edit leaderboard)+6
538Mistral NeMo Instruct (2407) · 8-bit Mistral44±1local~18GB128kOllama › WildEval ZeroEval published resultsLiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsEpoch AI — internal evaluationsWildBench v2 leaderboard data (Ai2)EvalPlus / EvalPerf published evaluation runsSpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)+9
540Phi-3-mini-4k-instruct (June 2024 update) · 8-bit Microsoft44±1local~5.8GBllama.cpp › WildEval ZeroEval published resultsLMArena leaderboard datasetEuroEval leaderboards (results collection), English generative leaderboard
541Yi 1.5 9B Chat · 8-bit 01.AI44±1local~13GB4kOllama › WildEval ZeroEval published resultsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4WildBench v2 leaderboard data (Ai2)CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)SpeakLeash Polish EQ-Bench leaderboardOpen Portuguese LLM Leaderboard (archived)+1
542Command R7B (12-2024) · 8-bit Cohere44±1local~12GB128kOllama › Cohere — Command A technical reportInception Arabic/Hindi leaderboards (AraGen-v3, HindiGen-v1, Arabic IFEval)Berkeley Function Calling Leaderboard result archiveOpen Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)
543Qwen2-Audio 7B Instruct · 8-bit Alibaba44±3local~10GBllama.cpp › AHELM: A Holistic Evaluation of Audio-Language Models (Stanford CRFM, arXiv:2508.21376v2)
544Gemma 3 4B · 8-bit Google44±1local~7.4GB131kOllama › Google DeepMind Gemma 3 270M IT model cardLFM2 Technical Report — Liquid AI own SmolLM3 evaluationMedmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 modelsGemma Team — Gemma 3 Technical ReportMIMIC Clinical Decision Making leaderboardLMArena leaderboard dataset+11
545Eurus-2-7B-PRIME · 8-bit PRIME-RL44±2local~10GB4kllama.cpp › PRIME-RL Eurus-2-7B-PRIME model card, Evaluation table (own models)Epoch AI — internal evaluations
546Llama 3.1 Tulu 3 8B · 8-bit Ai244±1local~12GB131kOllama › microsoft/Phi-4-mini-instruct model card2 OLMo 2 Furious (Team OLMo, Ai2) — authors' own evaluations of OLMo 2 Instruct and peer instruct modelsLMArena leaderboard datasetEuroEval leaderboards (results collection), English generative leaderboard
547Qwen2.5-VL 3B Instruct · 8-bit Alibaba44±1local~6.3GBOllama › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)
548Qwen1.5 32B Chat · 4-bit Alibaba44±1local~23GB32kOllama › BigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard datasetEpoch AI — internal evaluationsSpeakLeash Polish EQ-Bench leaderboardOpen Portuguese LLM Leaderboard (archived)
549Granite 20B Code Instruct (8K) · 4-bit IBM44±1local~15GBllama.cpp › Granite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4EuroEval leaderboards (results collection), English generative leaderboard
550Qwen2 7B Instruct · 8-bit Alibaba44±1local~12GB131kOllama › WildEval ZeroEval published resultsInternLM GitHub repository model cards (Shanghai AI Laboratory)LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsQwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)BigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4Inception Arabic/Hindi leaderboards (AraGen-v3, HindiGen-v1, Arabic IFEval)+4
551Falcon3 7B Instruct · 8-bit TII44±3local~11GB32kOllama › CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)Berkeley Function Calling Leaderboard result archiveOpen Portuguese LLM Leaderboard (archived)
552Xwin-LM 70B v0.1 · 2-bit Xwin-LM44±1local~28GBllama.cpp › Tulu 2 — base and instruction-tuned evaluationsAlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)
553Qwen3-VL 2B Instruct · 8-bit Alibaba44±1local~4.2GB256kOllama › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)CohereLabs/North-Micro-Vision-Instruct model card (benchmark table)ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)BEAR-Bench: A Bilingual Enterprise and Academic Reasoning Benchmark for Multimodal Models (arXiv:2608.17895v1)How Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings (arXiv:2605.07492v2)
554Dolphin 2.6 Mixtral 8x7B · 4-bit Cognitive Computations44±1local~29GBllama.cpp › EvalPlus / EvalPerf published evaluation runs
555Granite 8B Code Instruct (4K) · 4-bit IBM44±1local~6.6GBllama.cpp › Granite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4EuroEval leaderboards (results collection), English generative leaderboard
556Falcon3 10B Instruct · 8-bit TII44±3local~15GB32kOllama › CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)Berkeley Function Calling Leaderboard result archiveOpen Portuguese LLM Leaderboard (archived)
558Qwen3 1.7B · 8-bit Alibaba44±1local~4.6GB33kOllama › Marco-MoE: Open Multilingual Mixture-of-Expert Language Models with Efficient UpcyclingQwen/Qwen3.5-2B model cardQwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)LiquidAI/LFM2-1.2B model cardHuggingFaceTB/SmolLM3-3B model card (Evaluation section)LiquidAI/LFM2.5-1.2B-Thinking model card+10
559Phi-4-mini 3.8B · 8-bit Microsoft44±1local~6.9GB128kOllama › microsoft/Phi-4-mini-instruct model cardMicrosoft — Phi-4-Mini Technical ReportDaekeun Kim Korean LLM benchmark runsSpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)SpeakLeash Polish EQ-Bench leaderboardKorean Canonical Legal Benchmark: Toward Knowledge-Independent Evaluation of LLMs’ Legal Reasoning Capabilities+4
560Ministral 8B (2410) · 16-bit Mistral44±1local~22GB128khow to run › microsoft/Phi-4-mini-instruct model card2 OLMo 2 Furious (Team OLMo, Ai2) — authors' own evaluations of OLMo 2 Instruct and peer instruct modelsEpoch AI — internal evaluationsMistral AI vendor-reported benchmark scores for its own models (Hugging Face model cards)LMArena leaderboard datasetBRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)+6
561Granite 3.2 8B Instruct · 8-bit IBM44±1local~12GB131kOllama › ibm-granite/granite-3.3-8b-instruct model cardBerkeley Function Calling Leaderboard result archiveVectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
562Code Llama 70B Python · 2-bit Meta44±1local~28GB16kllama.cpp › Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsCode Llama: Open Foundation Models for Code — authors' own runs
563Llama 3.1 8B (base) · 16-bit Meta44±3local~18GBhow to run › Open Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)EuroEval leaderboards (results collection), English generative leaderboardOpen Portuguese LLM Leaderboard (archived)
564LFM2.5 1.2B Instruct · 4-bit Liquid AI44±2local~2.3GB33kllama.cpp › LiquidAI/LFM2.5-1.2B-Thinking model cardEuroEval leaderboards (results collection), English generative leaderboard
565Granite 3.0 8B Instruct · 8-bit IBM43±1local~12GB4kOllama › IBM Granite 3.0 Language Models technical report (GitHub)LMArena leaderboard datasetCodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)EuroEval leaderboards (results collection), English generative leaderboardVectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
566Phi-3.5-mini-instruct · 8-bit Microsoft43±1local~6.8GB128kOllama › microsoft/Phi-4-mini-instruct model cardWildEval ZeroEval published resultsLiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsDaekeun Kim Korean LLM benchmark runsMicrosoft — Phi-4-Mini Technical ReportSpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)+4
567Hermes 2 Theta Llama 3 8B · 16-bit Nous Research43±2local~18GB8khow to run › WildBench v2 leaderboard data (Ai2)SpeakLeash Polish EQ-Bench leaderboardOpen Portuguese LLM Leaderboard (archived)
568Yi 34B Chat · 4-bit 01.AI43±1local~24GB4kOllama › AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Arena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)Epoch AI — internal evaluationsLMArena leaderboard datasetEQ-Bench: An Emotional Intelligence Benchmark for Large Language Models — authors' own runs+1
569CogVLM2 Llama3 Chat 19B · 4-bit Zhipu AI (THUDM)43±3local (slow)~43GBhow to run › LMArena leaderboard datasetCapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era (arXiv:2503.12329v1)Zhipu AI (THUDM) CogVLM2 model card, Benchmark table (own models)
570Code Llama 70B (base) · 2-bit Meta43±1local~28GB16kllama.cpp › Granite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsCode Llama: Open Foundation Models for Code — authors' own runsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4
571Gemma 3n E2B IT · 8-bit Google43±2local~8.9GB32kOllama › Google DeepMind Gemma 3n E2B IT model cardOpen Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)EuroEval leaderboards (results collection), English generative leaderboardOpen Portuguese LLM Leaderboard (archived)
573T5 Small · 4-bit Google43±9local~1.8GB1khow to run › COPEN — EMNLP 2022 original zero-shot evaluations
574MiniCPM-V 2.6 · 8-bit OpenBMB43±2local~12GBOllama › CharXiv leaderboard (princeton-nlp/CharXiv README)LMArena leaderboard datasetCapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era (arXiv:2503.12329v1)PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding (arXiv:2501.16411v2)
575Qwen2.5 Coder 1.5B Instruct · 8-bit Alibaba43±1local~3.5GB33kllama.cpp › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)Aider code editing benchmark runs (old edit leaderboard)
576LFM2 2.6B · 4-bit Liquid AI43±2local~3.1GB33kllama.cpp › LFM2 Technical Report — Liquid AI own SmolLM3 evaluationEuroEval leaderboards (results collection), English generative leaderboard
577SmolLM3 3B · 8-bit Hugging Face43±1local~5.9GB66kllama.cpp › LFM2 Technical Report — Liquid AI own SmolLM3 evaluationHuggingFaceTB/SmolLM3-3B model card (Evaluation section)Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 modelsInception Arabic/Hindi leaderboards (AraGen-v3, HindiGen-v1, Arabic IFEval)EuroEval leaderboards (results collection), English generative leaderboardOpen Portuguese LLM Leaderboard (archived)
578Granite 3.1 8B Instruct · 8-bit IBM43±1local~12GB128kOllama › ibm-granite/granite-3.3-8b-instruct model cardibm-granite/granite-3.1-3b-a800m-instruct model cardLMArena leaderboard datasetBerkeley Function Calling Leaderboard result archiveOpen Portuguese LLM Leaderboard (archived)Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
579Llama 3.2 11B Vision Instruct · 8-bit Meta43±2local~16GB128kOllama › Pixtral 12B (Mistral AI, arXiv 2410.07073v2)LMArena leaderboard datasetInception Arabic/Hindi leaderboards (AraGen-v3, HindiGen-v1, Arabic IFEval)Open Portuguese LLM Leaderboard (archived)
580Qwen2.5 3B Instruct · 8-bit Alibaba43±1local~5.9GB33kOllama › microsoft/Phi-4-mini-instruct model cardWildEval ZeroEval published resultsSpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)Inception Arabic/Hindi leaderboards (AraGen-v3, HindiGen-v1, Arabic IFEval)CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)SpeakLeash Polish EQ-Bench leaderboard+5
581DeepSeek-Coder 1.3B Instruct · 8-bit DeepSeek43±1local~3GB16kOllama › EvalPlus / EvalPerf published evaluation runsTop Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4LiveCodeBench official website results (2024-12-26)CRUXEval published evaluation results (authors' generations and scores)CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)
582Aya 23 8B · 8-bit Cohere For AI43±3local~12GB8kOllama › SpeakLeash Polish EQ-Bench leaderboardOpen Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)Open Portuguese LLM Leaderboard (archived)EuroEval leaderboards (results collection), English generative leaderboard
583Phi-3-small-8k-instruct · 16-bit Microsoft43±2local~17GBhow to run › Arena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard datasetOpen Portuguese LLM Leaderboard (archived)
584CodeGemma 7B IT (v1.0) · 8-bit Google43±1local~11GBOllama › EvalPlus / EvalPerf published evaluation runsGranite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4CodeGemma: Open Code Models Based on Gemma — authors' own runs
585Aya Vision 32B Cohere42±3api price unknown~71GB16kdocs.cohere.com ↗LMArena leaderboard datasetKaleidoscope: In-language Exams for Massively Multilingual Vision Evaluation (arXiv:2504.07072v2)VMMU: A Vietnamese Multitask Multimodal Understanding and Reasoning Benchmark (arXiv:2508.13680v5)
586Tulu 2 DPO 70B · 4-bit Ai242±1local (slow)~45GBllama.cpp › Tulu 2 — base and instruction-tuned evaluationsAlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Arena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)WildBench v2 leaderboard data (Ai2)Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard dataset+1
587Mathstral 7B v0.1 · 8-bit Mistral AI42±1local~11GB32kOllama › LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsMMLU-Pro author-released evaluation runsWildEval ZeroEval published resultsMistral AI vendor-reported benchmark scores for its own models (Hugging Face model cards)
588Yi-1.5 9B (base) · 16-bit 01.AI42±2local~20GB4khow to run › Open Medical-LLM Leaderboard results (HF dataset openlifescienceai/results)BigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4EuroEval leaderboards (results collection), English generative leaderboardOpen Portuguese LLM Leaderboard (archived)
590Llama 3 8B Instruct · 8-bit Meta42±0local~12GB8kOllama › EvalPlus / EvalPerf published evaluation runsWildEval ZeroEval published resultsGranite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsInternLM GitHub repository model cards (Shanghai AI Laboratory)LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsAlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)+19
591WizardLM 70B V1.0 · 4-bit Microsoft42±1local (slow)~42GBOllama › Orca 2: Teaching Small Language Models How to Reason (Mitra et al., Microsoft)AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard datasetCodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)Open Portuguese LLM Leaderboard (archived)
592WizardCoder Python 13B V1.0 · 8-bit WizardLM42±2local~16GB16kOllama › WizardLM team vendor-reported scores for its own WizardCoder models (Hugging Face card)CRUXEval published evaluation results (authors' generations and scores)
593Hermes 3 Llama 3.1 8B · 8-bit Nous Research42±1local~12GB128kOllama › Nous Research vendor-reported scores for its own Hermes models (Hermes 3 Technical Report)Aider code editing benchmark runs (old edit leaderboard)Open Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)Open Portuguese LLM Leaderboard (archived)
594Falcon2 11B (base) · 8-bit TII42±3local~14GB8kllama.cpp › SpeakLeash Polish EQ-Bench leaderboardOpen Portuguese LLM Leaderboard (archived)EuroEval leaderboards (results collection), English generative leaderboard
595Granite 34B Code Base (8K) · 4-bit IBM42±1local~24GBllama.cpp › Granite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4
596speechless-starcoder2-7b · 4-bit uukuguy42±1local~17GBhow to run › EvalPlus / EvalPerf published evaluation runs
597Command R (03-2024) · 4-bit Cohere42±1local~24GB128kOllama › WildEval ZeroEval published resultsLiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsArena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)MMLU-Pro author-released evaluation runsWildBench v2 leaderboard data (Ai2)Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)+6
599OLMo 2 7B Instruct (1124) · 8-bit Allen Institute for AI42±1local~11GB4kOllama › 2 OLMo 2 Furious (Team OLMo, Ai2) — authors' own evaluations of OLMo 2 Instruct and peer instruct modelsallenai/Olmo-3-7B-Instruct model cardEuroEval leaderboards (results collection), English generative leaderboardOpen Portuguese LLM Leaderboard (archived)Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
600WizardCoder-15B-V1.0 · 8-bit WizardLM42±1local~19GBllama.cpp › EvalPlus / EvalPerf published evaluation runs
602Phi-3-vision-128k-instruct · 16-bit Microsoft41±2local~10GBhow to run › CharXiv leaderboard (princeton-nlp/CharXiv README)LMArena leaderboard datasetPhi-3 Technical Report (Microsoft, arXiv 2404.14219v3)PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding (arXiv:2501.16411v2)
603OpenChat 3.5 · 8-bit OpenChat41±2local~11GB8kOllama › OpenChat 3.5 model card (openchat/openchat_3.5)Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard datasetEQ-Bench: An Emotional Intelligence Benchmark for Large Language Models — authors' own runs
604InternVL2-4B · 16-bit Shanghai AI Laboratory (OpenGVLab)41±2local~10GBhow to run › OpenGVLab InternVL2 model cards (InternVL2-4B and InternVL2-26B), Evaluation tablesLMArena leaderboard datasetMicrosoft Phi-3.5-vision-instruct model card: Benchmarks tablePhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding (arXiv:2501.16411v2)
605Qwen1.5 14B Chat · 8-bit Alibaba41±1local~20GB32kOllama › Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsAlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)MMLU-Pro author-released evaluation runsPolyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard datasetInception Arabic/Hindi leaderboards (AraGen-v3, HindiGen-v1, Arabic IFEval)+3
606Code Llama 34B Python · 4-bit Meta41±1local~23GB16kllama.cpp › Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsCode Llama: Open Foundation Models for Code — authors' own runsCRUXEval published evaluation results (authors' generations and scores)
607speechless-coding-7b-16k-tora · 16-bit uukuguy41±1local~16GBhow to run › EvalPlus / EvalPerf published evaluation runs
608DeepSeek-Coder 33B Base · 4-bit DeepSeek41±1local~23GB16kOllama › EvalPlus / EvalPerf published evaluation runsTop Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsStarCoder 2 and The Stack v2: The Next Generation — authors' own runsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4CRUXEval published evaluation results (authors' generations and scores)
609InternLM2 Chat 20B · 8-bit Shanghai AI Laboratory (InternLM)41±1local~24GBllama.cpp › AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Arena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)SpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)SpeakLeash Polish EQ-Bench leaderboardOpen Portuguese LLM Leaderboard (archived)
610DeepSeek LLM 67B Chat · 2-bit DeepSeek41±1local~31GB4kllama.cpp › AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Epoch AI — internal evaluationsPolyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard datasetCodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)
611Llama 2 70B (base) · 4-bit Meta41±1local (slow)~43GB4kOllama › Mixtral of Experts — base-model evaluationsTulu 2 — base and instruction-tuned evaluationsMMLU-Pro author-released evaluation runsEuroEval leaderboards (results collection), English generative leaderboardOpen Portuguese LLM Leaderboard (archived)From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items (arXiv:2410.14897v1)
612Mixtral 8x7B v0.1 (base) · 4-bit Mistral AI41±1local~31GB32kOllama › Mixtral of Experts — base-model evaluationsGranite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsCRUXEval published evaluation results (authors' generations and scores)Open Portuguese LLM Leaderboard (archived)EuroEval leaderboards (results collection), English generative leaderboard
614CodeQwen1.5 7B (base) · 16-bit Alibaba41±1local~17GB66khow to run › EvalPlus / EvalPerf published evaluation runsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4
615Granite 4.0 1B · 16-bit IBM41±1local~6.1GB128kOllama › ibm-granite/granite-4.0-h-1b model cardLiquidAI/LFM2.5-1.2B-Thinking model cardEpoch AI — internal evaluations
616Mixtral 8x7B Instruct v0.1 · 4-bit Mistral41±1local~31GB32kOllama › EvalPlus / EvalPerf published evaluation runsWildEval ZeroEval published resultsTop Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsGranite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsAlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Arena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)+15
617Molmo 7B-D (0924) · 4-bit Ai241±1local (slow)~35GBhow to run › Pixtral 12B (Mistral AI, arXiv 2410.07073v2)Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding (Ai2, arXiv 2601.10611v4)LMArena leaderboard datasetKaleidoscope: In-language Exams for Massively Multilingual Vision Evaluation (arXiv:2504.07072v2)Ai2 Molmo-72B-0924 model card: Human Preference Elo Rating column
618OpenHermes-2.5-Code-290k-13B · 16-bit ajibawa-202341±1local~29GBhow to run › EvalPlus / EvalPerf published evaluation runs
619Granite 4.0 H 1B · 8-bit IBM40±1local~3.2GB131kOllama › ibm-granite/granite-4.0-h-1b model cardLiquidAI/LFM2.5-1.2B-Thinking model card
620Llama3-OpenBioLLM-8B · 16-bit Saama AI Labs40±2local~18GBhow to run › Open Medical-LLM Leaderboard results (HF dataset openlifescienceai/results)BRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)
621Nous Hermes 2 Mistral 7B DPO · 4-bit Nous Research40±2local~6.1GB33kllama.cpp › Open Medical-LLM Leaderboard results (HF dataset openlifescienceai/results)Open Portuguese LLM Leaderboard (archived)
622Nous Hermes 2 Mixtral 8x7B DPO · 4-bit Nous Research40±2local~31GB33kOllama › WildBench v2 leaderboard data (Ai2)Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard datasetOpen Portuguese LLM Leaderboard (archived)
623Deita 7B v1.0 · 4-bit HKUST NLP40±2local (slow)~32GBhow to run › AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Open Portuguese LLM Leaderboard (archived)
624Code Llama 34B Instruct · 4-bit Meta40±1local~23GB16kOllama › Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsGranite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsCode Llama: Open Foundation Models for Code — authors' own runsTulu 2 — base and instruction-tuned evaluationsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)+1
625Code Llama 34B (base) · 4-bit Meta40±1local~23GB16kllama.cpp › EvalPlus / EvalPerf published evaluation runsGranite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsStarCoder 2 and The Stack v2: The Next Generation — authors' own runsCode Llama: Open Foundation Models for Code — authors' own runsTulu 2 — base and instruction-tuned evaluationsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4+1
626Starling-LM 7B beta · 8-bit Nexusflow40±1local~11GB8kOllama › LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsOpen Medical-LLM Leaderboard results (HF dataset openlifescienceai/results)Arena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)WildBench v2 leaderboard data (Ai2)Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard dataset+3
627LFM2 1.2B · 4-bit Liquid AI40±2local~2.3GB33kllama.cpp › LiquidAI/LFM2-1.2B model cardEuroEval leaderboards (results collection), English generative leaderboardOpen Portuguese LLM Leaderboard (archived)
628Code Tulu 2 13B · 16-bit Allen Institute for AI40±2†local~29GBhow to run › Tulu 2 — base and instruction-tuned evaluations
629LLaVA-v1.6-34B · 4-bit LLaVA40±2local~24GB4kOllama › CharXiv leaderboard (princeton-nlp/CharXiv README)CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs (arXiv:2406.18521v1)LMArena leaderboard datasetCapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era (arXiv:2503.12329v1)LLaVA repository model zoo (haotian-liu/LLaVA docs/MODEL_ZOO.md)
630Bielik 1.5B v3.0 Instruct · 16-bit SpeakLeash40±3local~4.8GBhow to run › SpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)EuroEval leaderboards (results collection), English generative leaderboard
631OpenHermes 2.5 Mistral 7B · 8-bit Nous Research39±1local~11GBOllama › LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsOpenChat 3.5 model card (openchat/openchat_3.5)AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Hallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard dataset+2
632Granite 3.3 2B Instruct · 8-bit IBM39±1†local~4.3GB128kllama.cpp › ibm-granite/granite-3.3-8b-instruct model card
633Phi-3-mini-128k-instruct (Apr 2024) · 16-bit Microsoft39±2local~9.5GBhow to run › Arena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard datasetCodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)Open Portuguese LLM Leaderboard (archived)EuroEval leaderboards (results collection), English generative leaderboard+1
634Mistral 7B Instruct v0.3 · 8-bit Mistral39±1local~11GB32kOllama › LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsAlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Mistral AI vendor-reported benchmark scores for its own models (Hugging Face model cards)SpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)SpeakLeash Polish EQ-Bench leaderboardEpoch AI — internal evaluations+4
635Vicuna 33B v1.3 · 4-bit LMSYS39±1local~23GB2kOllama › AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Towards a Holistic Evaluation of LLMs on Factual Knowledge Recall (arXiv:2404.16164v1)Arena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard datasetLMSYS Chatbot Arena leaderboard Space: MT-Bench column of the published leaderboard table+2
636DeepSeek-Coder 6.7B Base · 8-bit DeepSeek39±1local~9.1GB16kOllama › EvalPlus / EvalPerf published evaluation runsTop Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsStarCoder 2 and The Stack v2: The Next Generation — authors' own runsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4CRUXEval published evaluation results (authors' generations and scores)
637Starling-LM 7B alpha · 8-bit UC Berkeley (NEST)39±1local~11GB8kOllama › AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Hallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)Arena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard datasetSpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)+2
638Granite 8B Code Base (4K) · 4-bit IBM39±1local~6.6GBllama.cpp › Granite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4EuroEval leaderboards (results collection), English generative leaderboard
639StarCoder2 15B · 8-bit BigCode39±1local~19GB16kOllama › EvalPlus / EvalPerf published evaluation runsTop Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsStarCoder 2 and The Stack v2: The Next Generation — authors' own runsGranite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4
640speechless-code-mistral-7b-v1.0 · 4-bit uukuguy39±1local~17GBhow to run › EvalPlus / EvalPerf published evaluation runsOpen Portuguese LLM Leaderboard (archived)
641Falcon-H1 3B Instruct · 16-bit TII39±4local~8.1GB131khow to run › Inception Arabic/Hindi leaderboards (AraGen-v3, HindiGen-v1, Arabic IFEval)Open Portuguese LLM Leaderboard (archived)
642Phi-2 (2.7B) · 4-bit Microsoft39±1local~7.3GB2khow to run › EvalPlus / EvalPerf published evaluation runsTop Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsMiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies (Hu et al.)AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)CRUXEval published evaluation results (authors' generations and scores)Open Portuguese LLM Leaderboard (archived)+2
643Granite 3.0 2B Instruct · 8-bit IBM39±1local~5.3GB4kOllama › IBM Granite 3.0 Language Models technical report (GitHub)LMArena leaderboard datasetCodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)EuroEval leaderboards (results collection), English generative leaderboardVectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
644Llama 2 70B Chat · 4-bit Meta39±1local (slow)~45GB4kllama.cpp › Orca 2: Teaching Small Language Models How to Reason (Mitra et al., Microsoft)Tulu 2 — base and instruction-tuned evaluationsAlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Arena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)WildBench v2 leaderboard data (Ai2)Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)+10
645Code Llama 13B Instruct · 8-bit Meta39±1local~16GB16kOllama › Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsCode Llama: Open Foundation Models for Code — authors' own runsGranite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsTulu 2 — base and instruction-tuned evaluationsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4
646MistralHermes-CodePro-7B-v1 · 16-bit beowolx39±1local~17GBhow to run › EvalPlus / EvalPerf published evaluation runs
647Llama-3-Instruct-8B-SimPO-v0.2 · 16-bit Princeton NLP39±1local~18GBhow to run › WildEval ZeroEval published resultsWildBench v2 leaderboard data (Ai2)Open Portuguese LLM Leaderboard (archived)
648Llama 3.2 3B Instruct · 8-bit Meta38±1local~6.1GB131kOllama › microsoft/Phi-4-mini-instruct model cardIBM Granite 3.0 Language Models technical report (GitHub)LFM2 Technical Report — Liquid AI own SmolLM3 evaluationAider code editing benchmark runs (old edit leaderboard)microsoft/Phi-4-mini-reasoning model cardMicrosoft — Phi-4-Mini Technical Report+11
649Qwen-14B-Chat · 16-bit Alibaba38±1local~31GBhow to run › Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsAlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard datasetEQ-Bench: An Emotional Intelligence Benchmark for Large Language Models — authors' own runs
651CodeGemma 7B (v1.0) · 8-bit Google38±1local~11GBOllama › EvalPlus / EvalPerf published evaluation runsGranite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsCodeGemma: Open Code Models Based on Gemma — authors' own runsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4
652Code Llama 13B Python · 8-bit Meta38±1local~16GB16kOllama › Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsCode Llama: Open Foundation Models for Code — authors' own runsCRUXEval published evaluation results (authors' generations and scores)
653Tulu 2 13B · 16-bit Allen Institute for AI38±2local~29GBhow to run › Tulu 2 — base and instruction-tuned evaluationsOpen Portuguese LLM Leaderboard (archived)
654Phi-3-mini-4k-instruct (Apr 2024) · 4-bit Microsoft38±2local~9.5GBllama.cpp › MMLU-Pro author-released evaluation runsPolyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard datasetSpeakLeash Polish EQ-Bench leaderboardOpen Portuguese LLM Leaderboard (archived)
655Apertus 8B Instruct (2509) · 16-bit Swiss AI38±4local~18GB66khow to run › allenai/Olmo-3-7B-Instruct model cardEuroEval leaderboards (results collection), English generative leaderboardMiðeind Icelandic LLM Leaderboard
657Granite 3B Code Instruct (2K) · 4-bit IBM38±2local~3.7GBllama.cpp › Granite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4EuroEval leaderboards (results collection), English generative leaderboard
658DeepSeek-V2 Lite Chat (16B-A2.4B) · 8-bit DeepSeek38±1local~22GB32kOllama › DeepSeek vendor-reported benchmark scores for its own models (Hugging Face model cards)LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsLiveCodeBench official website results (2024-12-26)CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)Open Portuguese LLM Leaderboard (archived)
659BioMistral-7B · 16-bit BioMistral38±3local~17GBhow to run › BRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)Reassessing High-Performing LLMs on Polish Medical Exams: True Competence or Bias-Driven Performance? (arXiv:2606.12250v1)SurgiQ: A Large-Scale Multi-Domain Benchmark for Evaluating Surgical Understanding in Large Language Models (arXiv:2606.08071v1)
660Qwen3.5 0.8B · 8-bit Alibaba38±1local~3.1GB262kOllama › Qwen/Qwen3.5-2B model cardEuroEval leaderboards (results collection), English generative leaderboardQwen/Qwen3.5-0.8B model cardChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)Knowledge Index of Noah's Ark (arXiv:2606.05104v2)BEAR-Bench: A Bilingual Enterprise and Academic Reasoning Benchmark for Multimodal Models (arXiv:2608.17895v1)+2
661Code Tulu 2 7B · 16-bit Allen Institute for AI38±2†local~16GBhow to run › Tulu 2 — base and instruction-tuned evaluations
662SOLAR 10.7B Instruct v1.0 · 8-bit Upstage37±1local~16GB4kOllama › EvalPlus / EvalPerf published evaluation runsOpen Medical-LLM Leaderboard results (HF dataset openlifescienceai/results)Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard datasetSpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)SpeakLeash Polish EQ-Bench leaderboard+2
663Phi-3.5-vision-instruct · 16-bit Microsoft37±2local~10GBhow to run › CohereLabs/North-Micro-Vision-Instruct model card (benchmark table)LMArena leaderboard datasetMicrosoft Phi-3.5-vision-instruct model card: Benchmarks tableAi2 Molmo-72B-0924 model card: Human Preference Elo Rating columnPhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding (arXiv:2501.16411v2)
664Tulu 2 DPO 13B · 16-bit Allen Institute for AI37±1local~29GBhow to run › Tulu 2 — base and instruction-tuned evaluationsAlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Open Portuguese LLM Leaderboard (archived)
665Yi-1.5 6B (base) · 16-bit 01.AI37±3local~14GB4khow to run › BigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4Open Portuguese LLM Leaderboard (archived)EuroEval leaderboards (results collection), English generative leaderboard
666Qwen2-VL 2B Instruct · 4-bit Alibaba37±1local~3.3GB33kllama.cpp › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
667DeepSeek R1 Distill Qwen 1.5B · 8-bit DeepSeek37±2local~4.3GB131kOllama › deepseek-ai/DeepSeek-R1 model cardCodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)BRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)Epoch AI — internal evaluationsTHINK-Bench: Evaluating Thinking Efficiency and Chain-of-Thought Quality of Large Reasoning Models (arXiv:2505.22113v1)EuroEval leaderboards (results collection), English generative leaderboard+1
668Gemma 2 2B IT · 8-bit Google37±1local~5.3GB8kOllama › IBM Granite 3.0 Language Models technical report (GitHub)WildEval ZeroEval published resultsWildBench v2 leaderboard data (Ai2)LMArena leaderboard datasetSpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)Open Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)+4
669Qwen2.5 Coder 0.5B Instruct · 4-bit Alibaba37±1local~2GB33kllama.cpp › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)Aider code editing benchmark runs (old edit leaderboard)
670Granite 20B Code Base (8K) · 4-bit IBM37±1local~15GBllama.cpp › Granite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4
671Gemma 1.1 7B IT · 8-bit Google37±1local~13GB8kOllama › EvalPlus / EvalPerf published evaluation runsLiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsOpen Medical-LLM Leaderboard results (HF dataset openlifescienceai/results)Arena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard dataset+2
672Code Llama 7B Python · 8-bit Meta37±1local~9.1GB16kOllama › Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsCode Llama: Open Foundation Models for Code — authors' own runsCRUXEval published evaluation results (authors' generations and scores)
673Dolphin 2.2.1 Mistral 7B · 8-bit Cognitive Computations37±2local~11GBOllama › AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard dataset
674Code Llama 13B (base) · 8-bit Meta37±1local~16GB16kOllama › EvalPlus / EvalPerf published evaluation runsStarCoder 2 and The Stack v2: The Next Generation — authors' own runsGranite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsCode Llama: Open Foundation Models for Code — authors' own runsTulu 2 — base and instruction-tuned evaluationsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4+1
675Qwen1.5 7B Chat · 8-bit Alibaba37±1local~12GB32kOllama › Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsLiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsAlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Open Medical-LLM Leaderboard results (HF dataset openlifescienceai/results)MMLU-Pro author-released evaluation runsWildBench v2 leaderboard data (Ai2)+4
676Yi 1.5 6B Chat · 8-bit 01.AI37±2local~9.7GB4kOllama › BigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4WildBench v2 leaderboard data (Ai2)SpeakLeash Polish EQ-Bench leaderboardOpen Portuguese LLM Leaderboard (archived)Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
677Falcon3 3B Instruct · 8-bit TII37±3local~6.1GB32kOllama › Berkeley Function Calling Leaderboard result archiveCodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)Open Portuguese LLM Leaderboard (archived)
678Zephyr 7B alpha · 8-bit Hugging Face36±1local~11GBOllama › LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsAlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Hallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard datasetOpen Portuguese LLM Leaderboard (archived)
679Vicuna 13B v1.5 · 8-bit LMSYS36±2local~18GB4kOllama › AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard datasetLMSYS Chatbot Arena leaderboard Space: MT-Bench column of the published leaderboard tableOpen Portuguese LLM Leaderboard (archived)
680Granite 3.1 2B Instruct · 8-bit IBM36±1local~5.2GB128kOllama › ibm-granite/granite-3.3-8b-instruct model cardibm-granite/granite-3.1-3b-a800m-instruct model cardLMArena leaderboard datasetSpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
681EXAONE 3.5 2.4B Instruct · 8-bit LG AI Research36±2local~5.1GB33kOllama › LG AI Research vendor-reported benchmark scores for its own EXAONE models (Hugging Face model cards)SpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)
683Code Llama 7B Instruct · 8-bit Meta36±1local~9.1GB16kOllama › Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsCode Llama: Open Foundation Models for Code — authors' own runsGranite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsTulu 2 — base and instruction-tuned evaluationsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4
684LFM2 700M · 4-bit Liquid AI36±2local~2GB33kllama.cpp › LiquidAI/LFM2-1.2B model cardEuroEval leaderboards (results collection), English generative leaderboardOpen Portuguese LLM Leaderboard (archived)
685Granite 3.2 2B Instruct · 8-bit IBM36±1local~5.2GB131kOllama › ibm-granite/granite-3.3-8b-instruct model cardVectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
686Mistral 7B Instruct v0.2 · 8-bit Mistral36±1local~11GB32kOllama › EvalPlus / EvalPerf published evaluation runsTop Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsGranite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsLiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsAlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Hallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)+9
687WizardLM 13B V1.2 · 4-bit Microsoft36±1local~29GBhow to run › Orca 2: Teaching Small Language Models How to Reason (Mitra et al., Microsoft)AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard datasetCodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)
688Tulu 2 7B · 16-bit Allen Institute for AI36±2local~16GBhow to run › Tulu 2 — base and instruction-tuned evaluationsOpen Portuguese LLM Leaderboard (archived)
689xDAN-L1-Chat-RL-v1 · 8-bit xDAN-AI36±1local~9.6GBllama.cpp › EvalPlus / EvalPerf published evaluation runs
690Llama 3 8B (base) · 16-bit Meta36±1local~18GBhow to run › EvalPlus / EvalPerf published evaluation runsOpen Medical-LLM Leaderboard results (HF dataset openlifescienceai/results)BigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4Open Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)EuroEval leaderboards (results collection), English generative leaderboard
691Mistral 7B v0.1 (base) · 16-bit Mistral AI36±0local~17GB8khow to run › EvalPlus / EvalPerf published evaluation runsStability AI — original StableLM zero-shot evaluation outputsMixtral of Experts — base-model evaluationsMiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies (Hu et al.)Mistral 7B — authors' own runsGemma report — original evaluations+4
692Qwen2.5 1.5B Instruct · 8-bit Alibaba36±1local~4GB33kOllama › 2 OLMo 2 Furious (Team OLMo, Ai2) — authors' own evaluations of OLMo 2 Instruct and peer instruct modelsSmolLM2 paper (Hugging Face) — authors' own instruct-model evaluationsSpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)SpeakLeash Polish EQ-Bench leaderboardOpen Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)+6
694Gemma 7B (base) · 8-bit Google35±1local~11GB8kOllama › EvalPlus / EvalPerf published evaluation runsGemma report — original evaluationsTop Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsGranite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsCodeGemma: Open Code Models Based on Gemma — authors' own runsOpen Medical-LLM Leaderboard results (HF dataset openlifescienceai/results)+3
695Tulu 2 DPO 7B · 16-bit Allen Institute for AI35±1local~16GBhow to run › Tulu 2 — base and instruction-tuned evaluationsAlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Open Portuguese LLM Leaderboard (archived)
696Eurus-2-7B-SFT · 8-bit PRIME-RL35±3†local~10GBllama.cpp › PRIME-RL Eurus-2-7B-PRIME model card, Evaluation table (own models)
697Falcon 40B (base) · 4-bit TII35±1local~28GB2kllama.cpp › MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies (Hu et al.)Hallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)Towards a Holistic Evaluation of LLMs on Factual Knowledge Recall (arXiv:2404.16164v1)Open Portuguese LLM Leaderboard (archived)From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items (arXiv:2410.14897v1)
698StarCoder2 7B · 8-bit BigCode35±1local~9.5GB16kOllama › EvalPlus / EvalPerf published evaluation runsTop Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsStarCoder 2 and The Stack v2: The Next Generation — authors' own runsGranite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4
699Granite 3.0 3B-A800M Instruct · 8-bit IBM35±1local~5.3GB4kllama.cpp › IBM Granite 3.0 Language Models technical report (GitHub)EuroEval leaderboards (results collection), English generative leaderboard
700DeepSeek LLM 7B Chat · 4-bit DeepSeek35±2†local~5.7GBOllama › DeepSeek vendor-reported benchmark scores for its own models (Hugging Face model cards)
701StarCoder 15.5B · 8-bit BigCode35±1local~19GBllama.cpp › EvalPlus / EvalPerf published evaluation runsTop Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runs
702Granite 3.1 3B-A800M Instruct · 8-bit IBM35±2†local~5.2GB131kllama.cpp › ibm-granite/granite-3.1-3b-a800m-instruct model card
703Llama 2 13B (base) · 8-bit Meta34±1local~16GB4kllama.cpp › Stability AI — original StableLM zero-shot evaluation outputsMixtral of Experts — base-model evaluationsMiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies (Hu et al.)Mistral 7B — authors' own runsTulu 2 — base and instruction-tuned evaluationsHallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)+3
704Code Llama 7B (base) · 8-bit Meta34±1local~9.1GB16kOllama › EvalPlus / EvalPerf published evaluation runsGranite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsStarCoder 2 and The Stack v2: The Next Generation — authors' own runsMistral 7B — authors' own runsCode Llama: Open Foundation Models for Code — authors' own runsTulu 2 — base and instruction-tuned evaluations+2
705Nous-Hermes-13b · 16-bit Nous Research34±2local~29GB2khow to run › AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Open Portuguese LLM Leaderboard (archived)
706ChatGLM3 6B 128K · 4-bit Zhipu AI (THUDM)34±4local~15GB131khow to run › NVIDIA RULER repository README results tableOpen Portuguese LLM Leaderboard (archived)
707Zephyr 7B beta · 8-bit Hugging Face34±1local~11GBOllama › EvalPlus / EvalPerf published evaluation runsTulu 2 — base and instruction-tuned evaluationsLiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsAlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Hallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)OpenChat 3.5 model card (openchat/openchat_3.5)+3
709Qwen3 0.6B · 8-bit Alibaba33±1local~3GB33kOllama › Olmo 3LiquidAI/LFM2-1.2B model cardBerkeley Function Calling Leaderboard result archiveOpen Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)BRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)EuroEval leaderboards (results collection), English generative leaderboard+4
710Llama 2 13B Chat · 8-bit Meta33±1local~18GB4kOllama › Orca 2: Teaching Small Language Models How to Reason (Mitra et al., Microsoft)Tulu 2 — base and instruction-tuned evaluationsAlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Hallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard dataset+9
711Flan-T5 XXL · 4-bit Google33±1local (slow)~49GBhow to run › Scaling Instruction-Finetuned Language Models — authors' own runsInstructEval (DeCLaRe Lab) README results tableTowards a Holistic Evaluation of LLMs on Factual Knowledge Recall (arXiv:2404.16164v1)LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion (arXiv:2306.02561v3)
712StarCoder2 3B · 8-bit BigCode33±1local~4.9GB16kOllama › EvalPlus / EvalPerf published evaluation runsTop Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsStarCoder 2 and The Stack v2: The Next Generation — authors' own runsGranite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4
713Granite 3B Code Base (2K) · 4-bit IBM33±1local~3.7GBllama.cpp › Granite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4EuroEval leaderboards (results collection), English generative leaderboard
715StarCoderBase 15.5B · 8-bit BigCode33±1local~19GBllama.cpp › StarCoder 2 and The Stack v2: The Next Generation — authors' own runsGranite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsCRUXEval published evaluation results (authors' generations and scores)
716Vicuna 7B v1.5 · 8-bit LMSYS33±1local~11GB4kOllama › LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsHallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard datasetLMSYS Chatbot Arena leaderboard Space: MT-Bench column of the published leaderboard table+1
718Stable Code 3B · 8-bit Stability AI33±1local~4.7GB16kOllama › EvalPlus / EvalPerf published evaluation runsTop Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsStarCoder 2 and The Stack v2: The Next Generation — authors' own runsGranite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runs
719OLMo 2 1B Instruct (0425) · 16-bit Allen Institute for AI33±2local~5.8GB4khow to run › 2 OLMo 2 Furious (Team OLMo, Ai2) — authors' own evaluations of OLMo 2 Instruct and peer instruct modelsOpen Portuguese LLM Leaderboard (archived)
720DeepSeek-Coder 1.3B Base · 8-bit DeepSeek32±1local~3GB16kOllama › EvalPlus / EvalPerf published evaluation runsTop Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsStarCoder 2 and The Stack v2: The Next Generation — authors' own runsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4CRUXEval published evaluation results (authors' generations and scores)
721Orca 2 13B · 8-bit Microsoft32±2local~16GB4kllama.cpp › Hallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
722Gemma 7B IT · 8-bit Google32±1local~13GB8kOllama › EvalPlus / EvalPerf published evaluation runsTop Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsGranite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsAlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)WildBench v2 leaderboard data (Ai2)Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)+5
723Mistral 7B Instruct v0.1 · 8-bit Mistral32±1local~9.6GB8kllama.cpp › Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsHallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)MMLU-Pro author-released evaluation runsPolyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard datasetOpen Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)+2
724Qwen1.5 4B Chat · 8-bit Alibaba32±2local~7GB32kOllama › LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsPolyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard datasetOpen Portuguese LLM Leaderboard (archived)EuroEval leaderboards (results collection), English generative leaderboard
725Ghost 7B Alpha · 16-bit Ghost X32±2local~17GBhow to run › AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Open Medical-LLM Leaderboard results (HF dataset openlifescienceai/results)
726CodeGemma 2B (v1.0) · 8-bit Google32±1local~4.3GBOllama › EvalPlus / EvalPerf published evaluation runsGranite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsCodeGemma: Open Code Models Based on Gemma — authors' own runsBigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4
727Qwen-7B (base) · 16-bit Alibaba32±1local~18GB33khow to run › Stability AI — original StableLM zero-shot evaluation outputsOpen Portuguese LLM Leaderboard (archived)
728Phi-1.5 (1.3B) · 4-bit Microsoft32±1local~4.5GB2khow to run › Stability AI — original StableLM zero-shot evaluation outputsTextbooks Are All You Need II: phi-1.5 technical report — authors' own runsOpen Medical-LLM Leaderboard results (HF dataset openlifescienceai/results)Open Portuguese LLM Leaderboard (archived)
729Falcon-H1 1.5B Instruct · 16-bit TII31±4local~4.8GB131khow to run › Inception Arabic/Hindi leaderboards (AraGen-v3, HindiGen-v1, Arabic IFEval)Open Portuguese LLM Leaderboard (archived)
730Flan-T5 XL · 4-bit Google31±2local~14GBhow to run › Scaling Instruction-Finetuned Language Models — authors' own runsInstructEval (DeCLaRe Lab) README results table
731Qwen2 1.5B Instruct · 8-bit Alibaba31±1local~4GB32kOllama › WildEval ZeroEval published resultsQwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)Qwen2-0.5B-Instruct model cardLiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsSpeakLeash Polish EQ-Bench leaderboardOpen Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)+1
732Qwen-7B-Chat · 16-bit Alibaba31±1local~18GB33khow to run › Stability AI — original StableLM zero-shot evaluation outputsOpen Portuguese LLM Leaderboard (archived)
733Gemma 3 1B · 4-bit Google31±1local~2.7GB32kOllama › Google DeepMind Gemma 3 270M IT model card2 OLMo 2 Furious (Team OLMo, Ai2) — authors' own evaluations of OLMo 2 Instruct and peer instruct modelsLiquidAI/LFM2-1.2B model cardLiquidAI/LFM2.5-1.2B-Thinking model cardMIMIC Clinical Decision Making leaderboardGemma Team — Gemma 3 Technical Report+7
734StarCoderBase 7B · 4-bit BigCode31±1local~6GBOllama › EvalPlus / EvalPerf published evaluation runsGranite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsStarCoder 2 and The Stack v2: The Next Generation — authors' own runsCRUXEval published evaluation results (authors' generations and scores)
735Llama 2 7B (base) · 8-bit Meta31±1local~9.1GB4kllama.cpp › Stability AI — original StableLM zero-shot evaluation outputsMixtral of Experts — base-model evaluationsOLMo: Accelerating the Science of Language Models — authors' own runsTextbooks Are All You Need II: phi-1.5 technical report — authors' own runsMistral 7B — authors' own runsMiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies (Hu et al.)+5
737LFM2 350M · 4-bit Liquid AI30±2local~1.7GB33kllama.cpp › LiquidAI/LFM2-1.2B model cardEuroEval leaderboards (results collection), English generative leaderboardOpen Portuguese LLM Leaderboard (archived)
738SmolLM2 1.7B Instruct · 8-bit Hugging Face30±1local~4.2GB8kOllama › 2 OLMo 2 Furious (Team OLMo, Ai2) — authors' own evaluations of OLMo 2 Instruct and peer instruct modelsSmolLM2 paper (Hugging Face) — authors' own instruct-model evaluationsLMArena leaderboard datasetSpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)EuroEval leaderboards (results collection), English generative leaderboard
739Llama 3.2 1B Instruct · 4-bit Meta30±1local~5.2GB131kOllama › IBM Granite 3.0 Language Models technical report (GitHub)2 OLMo 2 Furious (Team OLMo, Ai2) — authors' own evaluations of OLMo 2 Instruct and peer instruct modelsLiquidAI/LFM2-1.2B model cardSmolLM2 paper (Hugging Face) — authors' own instruct-model evaluationsLiquidAI/LFM2.5-1.2B-Thinking model cardLMArena leaderboard dataset+13
740Falcon 7B (base) · 16-bit TII30±1local~17GB2khow to run › Stability AI — original StableLM zero-shot evaluation outputsOLMo: Accelerating the Science of Language Models — authors' own runsTextbooks Are All You Need II: phi-1.5 technical report — authors' own runsHallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)Towards a Holistic Evaluation of LLMs on Factual Knowledge Recall (arXiv:2404.16164v1)Open Portuguese LLM Leaderboard (archived)+1
741Llama 2 7B Chat · 8-bit Meta30±1local~11GB4kOllama › Tulu 2 — base and instruction-tuned evaluationsLiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsAlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Hallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)WildBench v2 leaderboard data (Ai2)Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)+11
742Baichuan2-7B-Base · 16-bit Baichuan30±1local~17GBhow to run › Stability AI — original StableLM zero-shot evaluation outputsOpen Portuguese LLM Leaderboard (archived)
745OLMo 7B Instruct · 16-bit Ai229±2local~16GBhow to run › OLMo: Accelerating the Science of Language Models — authors' own runsPolyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard dataset
746StableLM-3B-4E1T · 16-bit Stability AI29±1local~7.4GB4khow to run › Stability AI — original StableLM zero-shot evaluation outputsOpen Portuguese LLM Leaderboard (archived)
747Gemma 2B (base) · 8-bit Google29±1local~4.3GB8kOllama › EvalPlus / EvalPerf published evaluation runsGemma report — original evaluationsTop Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runsGranite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsCodeGemma: Open Code Models Based on Gemma — authors' own runsHallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)+3
748OpenLLaMA 7B v2 · 4-bit OpenLM Research29±1local~16GBhow to run › Stability AI — original StableLM zero-shot evaluation outputsOpen Portuguese LLM Leaderboard (archived)
749Gemma 1.1 2B IT · 8-bit Google29±1local~5.2GB8kOllama › EvalPlus / EvalPerf published evaluation runsPolyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard datasetSpeakLeash Polish EQ-Bench leaderboardArena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)Open Portuguese LLM Leaderboard (archived)+1
750StableLM-Base-Alpha 7B v2 · 4-bit Stability AI29±1local~30GB4khow to run › Stability AI — original StableLM zero-shot evaluation outputsOpen Portuguese LLM Leaderboard (archived)
751Granite 3.1 1B-A400M Instruct · 8-bit IBM29±2†local~3GB131kOllama › ibm-granite/granite-3.1-3b-a800m-instruct model card
753NexusRaven V2 13B · 8-bit Nexusflow29±3local~16GB16kllama.cpp › Hallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)Berkeley Function Calling Leaderboard result archive
754OLMo 7B · 4-bit Allen Institute for AI28±1†local~30GB2khow to run › OLMo: Accelerating the Science of Language Models — authors' own runs
755Falcon 40B Instruct · 4-bit TII28±2local~29GBllama.cpp › AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)LMSYS Chatbot Arena leaderboard Space: MT-Bench column of the published leaderboard tableHallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)
756GPT-NeoX-20B · 8-bit EleutherAI28±1local~25GB2kllama.cpp › Stability AI — original StableLM zero-shot evaluation outputsGPT-NeoX-20B: An Open-Source Autoregressive Language Model — authors' own runsOpen Portuguese LLM Leaderboard (archived)
759StarCoderBase 3B · 4-bit BigCode28±1local~14GBhow to run › EvalPlus / EvalPerf published evaluation runsStarCoder 2 and The Stack v2: The Next Generation — authors' own runsGranite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runs
760Granite 3.0 1B-A400M Instruct · 8-bit IBM27±1local~3GB4kllama.cpp › IBM Granite 3.0 Language Models technical report (GitHub)EuroEval leaderboards (results collection), English generative leaderboard
761RedPajama-INCITE 7B Base · 4-bit Together27±1local~16GB2khow to run › Stability AI — original StableLM zero-shot evaluation outputsOLMo: Accelerating the Science of Language Models — authors' own runsOpen Portuguese LLM Leaderboard (archived)
762ChatGLM3-6B · 4-bit Zhipu AI (THUDM)27±2local~15GBhow to run › Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard datasetChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools (Team GLM, arXiv 2406.12793v2)Open Portuguese LLM Leaderboard (archived)
763Granite 4.0 H 350M · 8-bit IBM27±1†local~1.9GB33kOllama › ibm-granite/granite-4.0-h-1b model card
764Flan-T5 Large · 4-bit Google27±2local~4.8GBhow to run › Scaling Instruction-Finetuned Language Models — authors' own runsVectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
766Gemma 2B IT · 8-bit Google27±1local~5.2GB8kOllama › EvalPlus / EvalPerf published evaluation runsGranite Code Models: A Family of Open Foundation Models for Code Intelligence — authors' own runsWildBench v2 leaderboard data (Ai2)Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard datasetAlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)+3
767EuroLLM 1.7B Instruct · 16-bit UTTER (EuroLLM)27±3local~5GB4khow to run › SpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)Open Portuguese LLM Leaderboard (archived)EuroEval leaderboards (results collection), English generative leaderboard
768Qwen2.5 0.5B Instruct · 8-bit Alibaba27±2local~2.6GB33kOllama › HuggingFaceTB/SmolLM2-360M-Instruct model cardSpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)Open Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)Inception Arabic/Hindi leaderboards (AraGen-v3, HindiGen-v1, Arabic IFEval)Berkeley Function Calling Leaderboard result archiveVectara hallucination leaderboard (vectara/hallucination-leaderboard repository)+1
771OPT-13B (13 billion parameters) · 4-bit Meta26±1local~29GB2khow to run › Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling — authors' own runsHallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)Open Portuguese LLM Leaderboard (archived)
772Granite 4.0 350M · 16-bit IBM26±1local~2.9GB32kOllama › ibm-granite/granite-4.0-h-1b model cardBerkeley Function Calling Leaderboard result archiveEpoch AI — internal evaluations
775Falcon 7B Instruct · 8-bit TII25±2local~9.3GBllama.cpp › AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Hallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository)
776Qwen2 0.5B Instruct · 8-bit Alibaba25±2local~2.6GB32kOllama › Qwen2-0.5B-Instruct model cardLiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsOpen Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)Open Portuguese LLM Leaderboard (archived)
777Pythia 12B · 4-bit EleutherAI25±1local~27GB2khow to run › Stability AI — original StableLM zero-shot evaluation outputsPythia: A Suite for Analyzing Large Language Models Across Training and Scaling — authors' own runsTowards a Holistic Evaluation of LLMs on Factual Knowledge Recall (arXiv:2404.16164v1)Open Portuguese LLM Leaderboard (archived)
778RedPajama-INCITE Base 3B v1 · 4-bit Together25±3local~7.5GB2khow to run › RedPajama — original zero-shot 3B comparisonOpen Portuguese LLM Leaderboard (archived)
779ChatGLM2-6B · 4-bit Zhipu AI (THUDM)25±2local~15GBhow to run › AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard datasetLMSYS Chatbot Arena leaderboard Space: MT-Bench column of the published leaderboard tableOpen Portuguese LLM Leaderboard (archived)
780GPT-J 6B · 4-bit EleutherAI25±1local~14GB2khow to run › Stability AI — original StableLM zero-shot evaluation outputsEvalPlus / EvalPerf published evaluation runsGPT-NeoX-20B: An Open-Source Autoregressive Language Model — authors' own runsEleutherAI GPT-J-6B model card — EleutherAI lm-evaluation-harness runsHallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)Open Portuguese LLM Leaderboard (archived)
781OpenLLaMA 3B v2 · 4-bit OpenLM Research25±1local~8.7GBhow to run › Stability AI — original StableLM zero-shot evaluation outputsOpen Portuguese LLM Leaderboard (archived)
782OPT-6.7B · 4-bit Meta24±1local~16GB2khow to run › Stability AI — original StableLM zero-shot evaluation outputsPythia: A Suite for Analyzing Large Language Models Across Training and Scaling — authors' own runsOpen Portuguese LLM Leaderboard (archived)
784Falcon3 1B Instruct · 8-bit TII24±4local~4.1GB8kOllama › Berkeley Function Calling Leaderboard result archiveCodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)Open Portuguese LLM Leaderboard (archived)
785StableLM-Base-Alpha 3B v2 · 4-bit Stability AI24±1local~13GB4khow to run › Stability AI — original StableLM zero-shot evaluation outputsOpen Portuguese LLM Leaderboard (archived)
786Qwen1.5 1.8B Chat · 4-bit Alibaba24±2local~2.8GB33kllama.cpp › LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsAlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)EuroEval leaderboards (results collection), English generative leaderboardOpen Portuguese LLM Leaderboard (archived)
787Pythia 6.9B · 4-bit EleutherAI23±1local~16GB2khow to run › Stability AI — original StableLM zero-shot evaluation outputsOLMo: Accelerating the Science of Language Models — authors' own runsPythia: A Suite for Analyzing Large Language Models Across Training and Scaling — authors' own runsTowards a Holistic Evaluation of LLMs on Factual Knowledge Recall (arXiv:2404.16164v1)Open Portuguese LLM Leaderboard (archived)
788OpenAssistant SFT-4 Pythia 12B · 4-bit LAION (OpenAssistant)22±1local~27GBhow to run › InstructEval (DeCLaRe Lab) README results tableAlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard datasetLMSYS Chatbot Arena leaderboard Space: MT-Bench column of the published leaderboard tableLLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion (arXiv:2306.02561v3)
789Pythia 2.8B · 4-bit EleutherAI21±1local~7.5GB2khow to run › Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling — authors' own runsRedPajama — original zero-shot 3B comparisonOpen Medical-LLM Leaderboard results (HF dataset openlifescienceai/results)Open Portuguese LLM Leaderboard (archived)
790BLOOM 7.1B · 4-bit BigScience21±1local~16GB2khow to run › Stability AI — original StableLM zero-shot evaluation outputsBLOOM: A 176B-Parameter Open-Access Multilingual Language Model — authors' own runsHallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)Towards a Holistic Evaluation of LLMs on Factual Knowledge Recall (arXiv:2404.16164v1)Open Portuguese LLM Leaderboard (archived)From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items (arXiv:2410.14897v1)
791OLMo 1B · 4-bit Allen Institute for AI21±2†local~6.4GB2khow to run › OLMo: Accelerating the Science of Language Models — authors' own runs
792Phi-1 (1.3B) · 4-bit Microsoft21±4local~4.5GB2khow to run › CRUXEval published evaluation results (authors' generations and scores)Open Portuguese LLM Leaderboard (archived)
793Qwen1.5 0.5B Chat · 4-bit Alibaba21±3local~1.9GB33kllama.cpp › LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasetsEuroEval leaderboards (results collection), English generative leaderboardOpen Portuguese LLM Leaderboard (archived)
794ChatGLM-6B · 4-bit Zhipu AI (THUDM)20±2local~16GBhow to run › InstructEval (DeCLaRe Lab) README results tablePolyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard datasetLMSYS Chatbot Arena leaderboard Space: MT-Bench column of the published leaderboard tableLLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion (arXiv:2306.02561v3)
795Pythia 2.8B (deduped) · 4-bit EleutherAI20±1local~7.5GB2khow to run › Stability AI — original StableLM zero-shot evaluation outputsOpen Medical-LLM Leaderboard results (HF dataset openlifescienceai/results)Open Portuguese LLM Leaderboard (archived)
796Flan-T5 Base · 4-bit Google20±3†local~2.5GBhow to run › Scaling Instruction-Finetuned Language Models — authors' own runs
797Falcon-RW 1B · 16-bit TII20±2local~4.3GB2khow to run › Textbooks Are All You Need II: phi-1.5 technical report — authors' own runsHallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)
798OPT-2.7B · 4-bit Meta19±1local~7.1GB2khow to run › Stability AI — original StableLM zero-shot evaluation outputsPythia: A Suite for Analyzing Large Language Models Across Training and Scaling — authors' own runsOpen Portuguese LLM Leaderboard (archived)
799SmolLM2 360M Instruct · 4-bit Hugging Face19±3local~2.3GB8kOllama › HuggingFaceTB/SmolLM2-360M-Instruct model cardEuroEval leaderboards (results collection), English generative leaderboard
800GPT-Neo 2.7B · 4-bit EleutherAI18±1local~13GB2khow to run › EvalPlus / EvalPerf published evaluation runsTextbooks Are All You Need II: phi-1.5 technical report — authors' own runsEleutherAI GPT-J-6B model card — EleutherAI lm-evaluation-harness runsRedPajama — original zero-shot 3B comparisonHallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)EleutherAI GPT-Neo 2.7B model card — EleutherAI evaluation-harness runs+1
802Pythia 1.4B · 4-bit EleutherAI18±2local~4.6GB2khow to run › Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling — authors' own runsOpen Medical-LLM Leaderboard results (HF dataset openlifescienceai/results)
803BLOOM 3B · 4-bit BigScience18±1local~7.8GB2khow to run › Stability AI — original StableLM zero-shot evaluation outputsPythia: A Suite for Analyzing Large Language Models Across Training and Scaling — authors' own runsBLOOM: A 176B-Parameter Open-Access Multilingual Language Model — authors' own runsHallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)Open Portuguese LLM Leaderboard (archived)
804FastChat-T5 3B · 4-bit LMSYS17±2local~8.5GBhow to run › Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard datasetLMSYS Chatbot Arena leaderboard Space: MT-Bench column of the published leaderboard table
806OPT-1.3B · 4-bit Meta16±1local~4.3GB2khow to run › Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling — authors' own runsTextbooks Are All You Need II: phi-1.5 technical report — authors' own runsOpen Portuguese LLM Leaderboard (archived)
807Gemma 3 270M IT · 8-bit Google15±4local~2.4GB32kOllama › Google DeepMind Gemma 3 270M IT model cardEuroEval leaderboards (results collection), English generative leaderboardOpen Portuguese LLM Leaderboard (archived)
808Pythia 1B · 4-bit EleutherAI14±1local~3.7GB2khow to run › Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling — authors' own runsOLMo: Accelerating the Science of Language Models — authors' own runsOpen Medical-LLM Leaderboard results (HF dataset openlifescienceai/results)Open Portuguese LLM Leaderboard (archived)
809StableLM-Tuned-Alpha 7B · 8-bit Stability AI14±2local~10GBllama.cpp › Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)LMArena leaderboard datasetLMSYS Chatbot Arena leaderboard Space: MT-Bench column of the published leaderboard tableLLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion (arXiv:2306.02561v3)
810BLOOM 1.7B · 4-bit BigScience14±1local~5.1GB2khow to run › Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling — authors' own runsBLOOM: A 176B-Parameter Open-Access Multilingual Language Model — authors' own runsHallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)Open Portuguese LLM Leaderboard (archived)
811Flan-T5 Small · 4-bit Google14±3†local~1.8GBhow to run › Scaling Instruction-Finetuned Language Models — authors' own runs
812GPT-Neo 1.3B · 4-bit EleutherAI14±2local~7.1GB2khow to run › EleutherAI GPT-J-6B model card — EleutherAI lm-evaluation-harness runsHallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)EleutherAI GPT-Neo 2.7B model card — EleutherAI evaluation-harness runsOpen Portuguese LLM Leaderboard (archived)
813GPT-2 XL (1.5B) · 4-bit OpenAI11±1local~8.3GB1khow to run › Surface Form Competition (Holtzman et al., EMNLP 2021) — authors' own GPT-2 runsTextbooks Are All You Need II: phi-1.5 technical report — authors' own runsEleutherAI GPT-J-6B model card — EleutherAI lm-evaluation-harness runsPROST (Aroca-Ouellette et al., Findings of ACL-IJCNLP 2021) - authors' own zero-shot runsEleutherAI GPT-Neo 2.7B model card — EleutherAI evaluation-harness runsOpen Medical-LLM Leaderboard results (HF dataset openlifescienceai/results)+2
814BLOOM 1.1B · 4-bit BigScience11±1local~3.7GB2khow to run › Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling — authors' own runsBLOOM: A 176B-Parameter Open-Access Multilingual Language Model — authors' own runsHallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)
815Pythia 410M · 4-bit EleutherAI10±2local~2.5GB2khow to run › Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling — authors' own runsOpen Portuguese LLM Leaderboard (archived)
817StableLM-Base-Alpha 7B · 4-bit Stability AI9±1local (slow)~35GB4khow to run › Stability AI — original StableLM zero-shot evaluation outputsEvalPlus / EvalPerf published evaluation runsInstructEval (DeCLaRe Lab) README results tableOpen Portuguese LLM Leaderboard (archived)
818Zyte-1B · 4-bit venkycs (aihub-app)8±2local~3.8GBhow to run › EvalPlus / EvalPerf published evaluation runs
819GPT-Neo 125M · 4-bit EleutherAI5±5local~2.1GB2khow to run › Hallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)COPEN — EMNLP 2022 original zero-shot evaluationsOpen Portuguese LLM Leaderboard (archived)
820BLOOM 560M · 4-bit BigScience5±2local~2.7GB2khow to run › Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling — authors' own runsBLOOM: A 176B-Parameter Open-Access Multilingual Language Model — authors' own runsHallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)Open Portuguese LLM Leaderboard (archived)
821OPT-350M · 4-bit Meta5±2local~2.2GB2khow to run › Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling — authors' own runsOpen Portuguese LLM Leaderboard (archived)
822StableLM-Base-Alpha 3B · 4-bit Stability AI4±1local~17GB4khow to run › Stability AI — original StableLM zero-shot evaluation outputsOpen Portuguese LLM Leaderboard (archived)
823Pythia 160M · 4-bit EleutherAI3±2local~1.9GB2khow to run › Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling — authors' own runsOpen Portuguese LLM Leaderboard (archived)
824OPT-125M · 4-bit Meta3±2local~1.8GB2khow to run › Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling — authors' own runsOpen Portuguese LLM Leaderboard (archived)
825GPT-2 Large (774M) · 4-bit OpenAI1±2local~4.9GB1khow to run › Surface Form Competition (Holtzman et al., EMNLP 2021) — authors' own GPT-2 runsPROST (Aroca-Ouellette et al., Findings of ACL-IJCNLP 2021) - authors' own zero-shot runsCOPEN — EMNLP 2022 original zero-shot evaluationsEuroEval leaderboards (results collection), English generative leaderboardOpen Portuguese LLM Leaderboard (archived)
826GPT-2 Medium (355M) · 4-bit OpenAI-1±2local~3.1GB1khow to run › Surface Form Competition (Holtzman et al., EMNLP 2021) — authors' own GPT-2 runsPROST (Aroca-Ouellette et al., Findings of ACL-IJCNLP 2021) - authors' own zero-shot runsCOPEN — EMNLP 2022 original zero-shot evaluationsEuroEval leaderboards (results collection), English generative leaderboardOpen Portuguese LLM Leaderboard (archived)
827Pythia 70M · 4-bit EleutherAI-7±2local~1.7GB2khow to run › Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling — authors' own runsOpen Portuguese LLM Leaderboard (archived)
828GPT-2 Small (124M) · 4-bit OpenAI-9±3local~2.1GB1khow to run › Surface Form Competition (Holtzman et al., EMNLP 2021) — authors' own GPT-2 runsPROST (Aroca-Ouellette et al., Findings of ACL-IJCNLP 2021) - authors' own zero-shot runsCOPEN — EMNLP 2022 original zero-shot evaluationsEuroEval leaderboards (results collection), English generative leaderboardOpen Portuguese LLM Leaderboard (archived)
—Grok Build 0.1 SpaceXAI (xAI)no reviewed resultsapi $1.25/M256kdocs.x.ai ↗
—K2 Horizon 7B · gguf-q8_0 Institute of Foundation Models (MBZUAI)not scored yetlocal~13GB524kllama.cpp ›

+ 159 more don't fit your machine or budget · show them

+ 216 models with fewer than 3 results left off, since one or two tests say little about overall ability · show them

830 of 1134 catalogue models listed here · sources and licences

* new or thinly tested: ranked on too few benchmark results · † only the maker’s own numbers so far · ~RAM is estimated; full context may need more memory