1 Gemini 4 Argon (limited preview) Google 78±1 * limited preview 2 Claude Fable 5 Anthropic 76±1 * api $20.00/M 1M docs.anthropic.com ↗ 3 Claude Opus 4.6 Anthropic 76±1 * api $10.00/M 1M docs.anthropic.com ↗ 4 Claude Opus 5.5 Anthropic 76±1 * api $8.00/M 1M docs.anthropic.com ↗ 5 Claude Fable 5.1 Anthropic 75±1 * api $20.00/M 1M docs.anthropic.com ↗ 6 Claude Opus 4.7 Anthropic 75±1 * api $10.00/M 1M docs.anthropic.com ↗ 7 Gemini 3.8 Flash Google 75±1 * api $1.50/M 1M ai.google.dev ↗ 8 Muse Spark 1.3 Meta 75±1 * api $2.00/M 1M dev.meta.ai ↗ 9 Muse Spark 1.2 Meta 74±1 * api $2.00/M 1M dev.meta.ai ↗ 10 Muse Spark 1.1 Meta 74±1 * api $2.00/M 1M dev.meta.ai ↗ 11 Claude Opus 5 Anthropic 74±1 * api $10.00/M 1M docs.anthropic.com ↗ 12 Muse Spark Meta 74±1 * comparison only 13 Kimi K3 Moonshot AI 74±1 * api $6.00/M +local ~884GB 1M platform.moonshot.ai ↗ 14 Gemini 3.7 Flash Google 74±1 * api $1.50/M 1M ai.google.dev ↗ 15 Gemini 3.1 Pro (Preview) Google 74±1 * api $4.50/M 1M ai.google.dev ↗ 16 Gemini 3 Pro (Preview) Google 73±1 * comparison only 1M 17 GPT-5.6 Sol OpenAI 73±1 * api $8.00/M 1.1M platform.openai.com ↗ 18 Gemini 3.6 Flash Google 73±1 * api $1.50/M 1M ai.google.dev ↗ 19 GPT-6.1 Sol OpenAI 73±1 * api $4.00/M 1.1M developers.openai.com ↗ 20 Qwen3.8 Max (2.4T-A95B) Alibaba 73±1 * api $3.00/M +local ~380GB 262k deepinfra.com ↗ 21 GPT-5.5 OpenAI 73±1 * api $11.25/M 1.1M platform.openai.com ↗ 22 MiMo-V2.6-Pro Xiaomi 73±1 * api $0.54/M +local ~443GB 1M mimo.mi.com ↗ 23 Claude Opus 4.8 Anthropic 73±1 * api $10.00/M 1M docs.anthropic.com ↗ 24 GLM-5.3 Z.ai 73±1 * api $2.15/M +local ~239GB 1M docs.z.ai ↗ 25 GPT-6 Astra OpenAI 72±1 * api $20.00/M 1.1M platform.openai.com ↗ 26 Gemini 3.5 Flash Google 72±1 * api $3.38/M 1M ai.google.dev ↗ 27 GLM-5.2 Z.ai 72±1 * api $2.15/M +local ~121GB 1M docs.z.ai ↗ 28 GPT-5.4 OpenAI 72±1 * api $5.63/M 1.1M platform.openai.com ↗ 29 DeepSeek V4.1 Flash DeepSeek 72±1 * api $0.26/M +local ~537GB 1M api-docs.deepseek.com ↗ 30 GLM-5.3-Flash Z.ai 72±1 * api $0.24/M +local ~103GB 1M docs.z.ai ↗ 31 Claude Opus 4.5 Anthropic 72±1 * api $10.00/M 200k docs.anthropic.com ↗ 32 GPT-5.5 Instant OpenAI 72±1 * comparison only 33 Claude Sonnet 4.6 Anthropic 72±1 * api $6.00/M 1M docs.anthropic.com ↗ 34 Gemini 3 Flash (Preview) Google 72±1 * api $1.13/M 1M ai.google.dev ↗ 35 Grok 4.20 (0309 reasoning) SpaceXAI (xAI) 72±1 * api $1.56/M 1M docs.x.ai ↗ 36 Grok 4.20 Multi-Agent (0309) SpaceXAI (xAI) 72±1 * api $1.56/M 1M docs.x.ai ↗ 37 Claude Sonnet 5.5 Anthropic 72±1 * api $4.00/M 1M platform.claude.com ↗ 38 MiMo-V2.5-Pro (1T-A42B) Xiaomi 71±1 * api $0.65/M +local ~163GB 1M novita.ai ↗ 39 GPT-5.6 Terra OpenAI 71±1 * api $4.50/M 1.1M platform.openai.com ↗ 40 Grok 4.5 SpaceXAI (xAI) 71±1 * api $3.00/M 500k docs.x.ai ↗ 41 DeepSeek V4 Pro (0813) DeepSeek 71±1 * api $1.63/M +local ~1010GB 1M deepinfra.com ↗ 42 GLM-5.1 Z.ai 71±1 * api $2.15/M +local ~119GB 200k docs.z.ai ↗ 43 Claude Sonnet 5 Anthropic 70±1 * api $4.00/M 1M docs.anthropic.com ↗ 44 Kimi K2.6 Moonshot AI 70±1 * api $1.71/M +local ~317GB 262k platform.moonshot.ai ↗ 45 Qwen3.6 Max Preview Alibaba 70±1 * api $2.92/M 256k www.alibabacloud.com ↗ 46 GPT-6 Sol OpenAI 70±1 * api $4.00/M 1.1M platform.openai.com ↗ 47 GLM-5 Z.ai 70±1 * api $1.55/M +local ~119GB 205k docs.z.ai ↗ 48 Claude Sonnet 4.5 Anthropic 70±1 * api $6.00/M 200k docs.anthropic.com ↗ 49 Dola Seed 2.0 Pro ByteDance 70±1 * comparison only 50 GPT-5.1 OpenAI 70±1 * api $3.44/M 400k platform.openai.com ↗ 51 Qwen3.7 Plus Alibaba 70±1 * api $0.70/M 1M www.alibabacloud.com ↗ 52 Hunyuan Hy3 (295B-A21B) Tencent 70±1 * api $0.23/M +local ~96GB 256k deepinfra.com ↗ 53 Gemini 3.5 Flash-Lite Google 70±1 * api $0.85/M 1M ai.google.dev ↗ 54 DeepSeek V4 Pro (Preview, Apr 2026) DeepSeek 69±1 * local ~604GB llama.cpp › copy 55 Grok 4.6 SpaceXAI (xAI) 69±1 * api $3.00/M 500k docs.x.ai ↗ 56 Step 5 Preview StepFun 69±1 * comparison only 57 Gemma 4 31B Google 69±1 * api $0.19/M +local ~21GB 262k deepinfra.com ↗ 58 GPT-5.6 Luna OpenAI 69±1 * api $0.45/M 1.1M platform.openai.com ↗ 59 MiMo-V2.6-Flash (309B-A15B) Xiaomi 69±1 * api $0.17/M +local ~136GB 1M mimo.mi.com ↗ 60 Kimi K2.5 Moonshot AI 69±1 * api $1.20/M +local ~160GB 262k docs.aws.amazon.com ↗ 61 Claude Opus 4.1 Anthropic 69±1 * comparison only 62 MiMo-V2-Pro Xiaomi 69±1 * comparison only 63 GPT-5.4 mini OpenAI 69±1 * api $1.69/M 400k platform.openai.com ↗ 64 Gemini 2.5 Pro Google 68±1 * api $3.44/M 1M ai.google.dev ↗ 65 Qwen3.6 Plus Alibaba 68±1 * api $1.13/M 1M docs.together.ai ↗ 66 GPT-6 Luna OpenAI 68±1 * api $0.20/M 1.1M platform.openai.com ↗ 67 Grok 4.7 SpaceXAI (xAI) 68±1 * api $3.00/M 500k docs.x.ai ↗ 68 ChatGPT-4o (2025-03-26) OpenAI 68±1 * comparison only 69 Grok 4.3 SpaceXAI (xAI) 68±1 * api $1.56/M 1M docs.x.ai ↗ 70 GLM-4.7 Z.ai 68±1 * api $1.00/M +local ~58GB 205k docs.z.ai ↗ 71 Inkling (975B-A41B) Thinking Machines 68±1 * api $1.73/M +local ~156GB 1M deepinfra.com ↗ 72 Nemotron Cascade 2 30B-A3B NVIDIA 68±4 * † local ~20GB 256k LM Studio › copy 73 Qwen3.5 397B-A17B Alibaba 68±1 * api $1.09/M +local ~65GB 262k deepinfra.com ↗ 74 MiniMax-M3 MiniMax 68±1 * api $0.48/M +local ~137GB 1M deepinfra.com ↗ 75 GPT-4.5 Preview OpenAI 68±1 comparison only 76 DeepSeek V4 Flash (Preview, Apr 2026) DeepSeek 67±1 * local ~103GB llama.cpp › copy 77 Qwen3.8 27B Alibaba 67±1 * api $1.60/M +local ~18GB 262k console.groq.com ↗ 78 Gemma 4 26B-A4B Google 67±1 * api $0.14/M +local ~18GB 262k deepinfra.com ↗ 79 GPT-5.2 OpenAI 67±1 * api $4.81/M 400k platform.openai.com ↗ 80 o3 OpenAI 67±1 api $3.50/M 200k platform.openai.com ↗ 81 GPT-5 OpenAI 67±1 * api $3.44/M 400k platform.openai.com ↗ 82 MiMo-V2.5 (310B-A15B) Xiaomi 67±1 * api $0.21/M +local ~100GB 1M novita.ai ↗ 83 Gemma 4 12B Google 67±6 * local ~8.5GB 262k LM Studio › copy 84 GLM-5V-Turbo Z.ai 67±1 * api $1.90/M 200k www.siliconflow.com ↗ 85 Gemini 3.1 Flash-Lite Google 67±1 * api $0.56/M 1M ai.google.dev ↗ 86 MiMo-V2-Omni Xiaomi 66±1 * comparison only 262k 87 Kimi K2 Thinking Moonshot AI 66±1 * api $1.07/M +local ~160GB 262k docs.aws.amazon.com ↗ 88 Grok 4.1 Fast (Reasoning) SpaceXAI (xAI) 66±1 * api $0.28/M 128k azure.microsoft.com ↗ 89 Mistral Large 4 (public preview) Mistral 66±1 * api $2.06/M 1M docs.mistral.ai ↗ 90 Mistral Medium 3.5 (128B) Mistral 66±1 * api $3.00/M +local ~42GB 262k docs.mistral.ai ↗ 91 Nemotron 3 Ultra 550B-A55B NVIDIA 66±1 * api $1.35/M +local ~89GB 1M docs.together.ai ↗ 92 Claude Opus 4 Anthropic 66±1 * comparison only 93 Muse Glimmer 30B Meta 66±1 * api $0.64/M +local ~19GB 131k fireworks.ai ↗ 94 DeepSeek V3.2 Exp DeepSeek 66±1 * local ~726GB how to run › copy 95 GLM-4.6 Z.ai 66±1 * api $1.00/M +local ~58GB 205k docs.z.ai ↗ 96 DeepSeek V3.2 DeepSeek 65±1 * api $0.29/M +local ~110GB 128k deepinfra.com ↗ 97 Qwen3-Max (2025-09-23) Alibaba 65±1 * api $2.40/M 262k www.alibabacloud.com ↗ 98 DeepSeek R1 0528 DeepSeek 65±1 * api $0.91/M +local ~110GB 164k deepinfra.com ↗ 99 Qwen3 235B-A22B Instruct 2507 Alibaba 65±1 api $0.20/M +local ~76GB 262k deepinfra.com ↗ 100 Kimi K2 Instruct (0905) Moonshot AI 65±1 * local ~298GB llama.cpp › copy 101 Kimi K2 Instruct (0711) Moonshot AI 65±1 * api $1.00/M +local ~160GB 131k novita.ai ↗ 102 DeepSeek V3.1 Terminus DeepSeek 65±1 * local ~230GB 164k llama.cpp › copy 103 Qwen3.5 122B-A10B Alibaba 65±1 * api $1.10/M +local ~75GB 262k www.alibabacloud.com ↗ 104 MiniMax-M2.7 MiniMax 64±1 * api $0.53/M +local ~75GB 205k platform.minimax.io ↗ 105 Claude Haiku 4.5 Anthropic 64±1 * api $2.00/M 200k docs.anthropic.com ↗ 106 Qwen3-Max (2026-01-23) Alibaba 64±5 * † comparison only 107 DeepSeek V3.1 DeepSeek 64±1 api $0.42/M +local ~110GB 131k deepinfra.com ↗ 108 Mistral Large 3 (675B-A41B) Mistral 64±1 * api $0.75/M +local ~108GB 262k docs.mistral.ai ↗ 109 Qwen3-VL 235B-A22B Instruct Alibaba 64±1 local ~134GB 256k LM Studio › copy 110 Grok 4 (0709) SpaceXAI (xAI) 64±1 * comparison only 111 Spark-X2.5 4B iFLYTEK (SparkLLM) 64±6 * † local ~3.9GB 1M LM Studio › copy 112 GPT-4.1 OpenAI 64±1 api $3.50/M 1M platform.openai.com ↗ 113 Qwen3.5 27B Alibaba 64±1 * api $0.84/M +local ~18GB 262k deepinfra.com ↗ 114 GLM-4.5 Z.ai 64±1 api $1.00/M +local ~58GB 131k docs.z.ai ↗ 115 Hy3 preview (295B-A21B) Tencent 64±1 * local ~629GB how to run › copy 116 Mistral Medium 3.1 (2508) Mistral 64±1 * comparison only 117 Gemini 2.5 Flash Google 63±1 * api $0.85/M 1M ai.google.dev ↗ 118 K-EXAONE 2.0 (750B-A37B) LG AI Research 63±4 * † local ~791GB 262k how to run › copy 119 Inkling Small (266B-A12B) Thinking Machines 63±1 * api $0.64/M +local ~86GB 1M deepinfra.com ↗ 120 Grok 4 Fast SpaceXAI (xAI) 63±1 * comparison only 121 o1 (2024-12-17) OpenAI 63±1 api $26.25/M 200k developers.openai.com ↗ 122 Gemini 2.5 Flash Preview (09-2025) Google 63±1 * comparison only 123 LongCat-Flash-Chat (560B-A27B) Meituan 63±1 * local ~333GB 128k LM Studio › copy 124 Nemotron-Cascade-8B NVIDIA 63±7 * † local ~6.3GB LM Studio › copy 125 GPT-5.4 nano OpenAI 63±1 * api $0.46/M 400k platform.openai.com ↗ 126 Qwen3 235B-A22B Thinking 2507 Alibaba 63±1 api $0.97/M +local ~76GB 131k novita.ai ↗ 127 Claude Sonnet 4 Anthropic 63±1 * comparison only 128 Qwen3-Next 80B-A3B Instruct Alibaba 63±1 api $0.34/M +local ~27GB 131k deepinfra.com ↗ 129 DeepSeek R1 (Jan '25) DeepSeek 63±1 api $4.00/M +local ~110GB 128k docs.together.ai ↗ 130 Qwen3.5 Flash Alibaba 62±1 * api $0.17/M 1M www.alibabacloud.com ↗ 131 LFM2.5 2.6B Liquid AI 62±7 * local ~3.2GB 131k LM Studio › copy 132 o4-mini OpenAI 62±1 api $1.93/M 200k platform.openai.com ↗ 133 DeepSeek V3 0324 DeepSeek 62±1 * local ~108GB 164k llama.cpp › copy 134 Step 3.5 Flash (196B-A11B) StepFun 62±1 * api $0.15/M +local ~118GB 256k platform.stepfun.ai ↗ 135 Qwen3-VL 235B-A22B Thinking Alibaba 62±1 * local ~111GB 256k LM Studio › copy 136 Qwen3.5 35B-A3B Alibaba 62±1 api $0.35/M +local ~23GB 262k deepinfra.com ↗ 137 MiniMax-M2.5 MiniMax 61±1 * api $0.53/M +local ~75GB 205k platform.minimax.io ↗ 138 Claude 3.7 Sonnet Anthropic 61±1 comparison only 139 GPT-5 mini OpenAI 61±1 * api $0.69/M 400k platform.openai.com ↗ 140 o1-preview OpenAI 61±1 * comparison only 141 Qwen3-Coder 480B-A35B Instruct Alibaba 61±1 * api $0.67/M +local ~78GB 262k novita.ai ↗ 142 Mistral Medium 3 (2505) Mistral 61±1 * comparison only 143 Solar Pro 4 Upstage 61±1 * api $0.53/M 524k developers.upstage.ai ↗ 144 MiMo-V2-Flash (309B-A15B) Xiaomi 61±1 * local ~108GB llama.cpp › copy 145 MiniMax-M2.1 MiniMax 61±1 * local ~79GB llama.cpp › copy 146 LFM2.5 8B-A1B Liquid AI 60±5 * local ~6.5GB 128k LM Studio › copy 147 LongCat-Flash-Thinking (560B-A27B) Meituan 60±5 * † comparison only 128k 148 Qwen3 30B-A3B Instruct 2507 Alibaba 60±1 api $0.15/M +local ~20GB 262k tokenfactory.nebius.com ↗ 149 GPT-4.1 mini OpenAI 60±1 api $0.70/M 1M platform.openai.com ↗ 150 GLM-4.6V Z.ai 60±1 * api $0.45/M +local ~51GB 128k docs.z.ai ↗ 151 Trinity-Large-Preview Arcee AI 60±1 * local ~155GB llama.cpp › copy 152 LongCat 2.0 (1.6T-A48B) Meituan 60±7 * † api $1.30/M +local ~2155GB 1M longcat.chat ↗ 153 K-EXAONE (236B-A23B) LG AI Research 60±3 * † local ~152GB 262k llama.cpp › copy 154 Spark-X2.5 1.7B iFLYTEK (SparkLLM) 60±5 * † local ~2.7GB 1M llama.cpp › copy 155 Gemini 2.5 Flash-Lite Preview (06-17) Google 59±1 * comparison only 156 Qwen3 235B-A22B (Apr 2025, hybrid) Alibaba 59±1 api $1.23/M +local ~76GB 131k www.alibabacloud.com ↗ 157 GLM-4.5-Air Z.ai 59±1 * api $0.42/M +local ~35GB 131k docs.z.ai ↗ 158 Qwen2.5-Max (2025-01-25) Alibaba 59±1 * comparison only 159 Gemma 2 9B IT DPO (Princeton) Princeton NLP 59±2 * local ~7.6GB llama.cpp › copy 160 Qwen3-Next 80B-A3B Thinking Alibaba 59±1 api $0.41/M +local ~27GB 131k www.alibabacloud.com ↗ 161 o3-mini OpenAI 59±1 api $1.93/M 200k developers.openai.com ↗ 162 Claude 3.5 Sonnet (2024-10-22) Anthropic 59±1 comparison only 163 EXAONE 4.5 33B LG AI Research 59±4 * † local ~24GB 262k llama.cpp › copy 164 LFM2.5 1.2B Thinking Liquid AI 59±6 * † local ~2.2GB 33k LM Studio › copy 165 Trinity-Large-Thinking Arcee AI 58±1 * api $0.39/M +local ~141GB 512k docs.arcee.ai ↗ 166 GLM-4.7-Flash Z.ai 58±1 * api $0.0000/M +local ~19GB 200k docs.z.ai ↗ 167 MiniMax-M1 (80k) MiniMax 58±1 * api $0.96/M +local ~959GB 1M novita.ai ↗ 168 Grok 3 Mini Beta SpaceXAI (xAI) 58±1 * comparison only 169 Qwen3.5 9B Alibaba 58±3 api $0.11/M +local ~7.4GB 262k deepinfra.com ↗ 170 Gemma 3 27B Google 58±1 api $0.10/M +local ~18GB 131k deepinfra.com ↗ 171 Qwen3 30B-A3B Thinking 2507 Alibaba 58±2 api $0.75/M +local ~20GB 262k www.alibabacloud.com ↗ 172 Nemotron 3 Super 120B-A12B NVIDIA 58±1 * api $0.28/M +local ~73GB 262k docs.aws.amazon.com ↗ 173 DeepSeek V3 (Dec '24) DeepSeek 57±1 api $0.46/M +local ~337GB 131k deepinfra.com ↗ 174 Gemini 2.0 Flash (001) Google 57±1 * comparison only 175 Granite 4.1 30B IBM 57±5 * † local ~19GB Ollama › copy 176 Phi-4-reasoning-plus 14B Microsoft 57±3 † local ~10GB LM Studio › copy 177 Qwen3-VL 32B Thinking Alibaba 57±3 * † api $0.28/M +local ~22GB 256k www.alibabacloud.com ↗ 178 Mistral Small 3.2 24B Mistral 57±1 * api $0.11/M +local ~16GB 128k deepinfra.com ↗ 179 INTELLECT-3 Prime Intellect 57±1 * local ~48GB llama.cpp › copy 180 Command A (03-2025) Cohere 57±1 * api $4.38/M +local ~37GB 256k azure.microsoft.com ↗ 181 Gemini 2.0 Flash-Lite Preview (02-05) Google 57±1 * comparison only 182 GLM-4.5V Z.ai 57±1 * api $0.90/M +local ~69GB 64k docs.z.ai ↗ 183 gpt-oss-120b OpenAI 56±1 * api $0.26/M +local ~67GB 131k console.groq.com ↗ 184 Gemini 1.5 Pro (002) Google 56±1 * comparison only 185 Llama 3.1 Nemotron Ultra 253B v1 NVIDIA 56±1 local ~82GB 128k llama.cpp › copy 186 Nemotron 3.5 Lightning 30B-A3B NVIDIA 56±1 * api $0.087/M +local ~20GB 262k fireworks.ai ↗ 187 Qwen3.5 4B Alibaba 56±3 local ~4.3GB 262k llama.cpp › copy 188 Nemotron 3 Nano 4B NVIDIA 56±6 * local ~3.8GB 262k LM Studio › copy 189 LFM2.5 1.2B Instruct Liquid AI 56±6 * † local ~2.2GB 33k LM Studio › copy 190 Qwen3 32B Alibaba 56±1 api $0.13/M +local ~20GB 131k deepinfra.com ↗ 191 Qwen Plus (2025-01-25) Alibaba 56±1 * api $0.60/M 131k www.alibabacloud.com ↗ 192 QwQ-32B Alibaba 56±1 local ~21GB 131k LM Studio › copy 193 Mellum2.1 12B-A2.5B Thinking JetBrains 56±8 * † local ~8.3GB LM Studio › copy 194 MiniMax-M2 MiniMax 55±1 * api $0.53/M +local ~75GB 205k docs.aws.amazon.com ↗ 195 Llama 3.3 Nemotron Super 49B v1.5 NVIDIA 55±1 * local ~18GB 131k llama.cpp › copy 196 o1-mini OpenAI 55±1 * comparison only 197 Mercury 2 Inception 55±1 * comparison only 198 Gemma 3 12B Google 55±1 * api $0.075/M +local ~9.1GB 131k deepinfra.com ↗ 199 Granite 4.2 30B IBM 55±1 * api $0.28/M +local ~19GB 131k deepinfra.com ↗ 200 GPT-4o (2024-05-13) OpenAI 55±1 api $7.50/M 128k developers.openai.com ↗ 201 Qwen3-VL 30B-A3B Instruct Alibaba 55±3 * † api $0.35/M +local ~21GB 256k www.alibabacloud.com ↗ 202 MiniCPM5 2B OpenBMB 55±6 * † local ~3GB 131k LM Studio › copy 203 GPT-5 nano OpenAI 55±1 * api $0.14/M 400k platform.openai.com ↗ 204 Claude 3.5 Sonnet (2024-06-20) Anthropic 55±1 comparison only 205 Phi-4-reasoning 14B Microsoft 54±3 † api $0.22/M +local ~10GB 33k azure.microsoft.com ↗ 206 Nova 2 Lite Amazon 54±1 * api $0.94/M 1M docs.aws.amazon.com ↗ 207 GPT-4o (2024-08-06) OpenAI 54±1 api $4.38/M 128k developers.openai.com ↗ 208 Qwen3 8B Alibaba 54±3 * † api $0.31/M +local ~6.1GB 33k www.alibabacloud.com ↗ 209 Qwen3 4B Instruct 2507 Alibaba 54±2 † local ~3.9GB 262k LM Studio › copy 210 Qwen3-VL 32B Instruct Alibaba 54±3 * † api $0.28/M +local ~22GB 256k www.alibabacloud.com ↗ 211 Llama 3.3 Nemotron Super 49B v1 NVIDIA 54±1 local ~22GB llama.cpp › copy 212 Nemotron Nano 9B v2 NVIDIA 54±3 api $0.10/M +local ~7.6GB 131k docs.aws.amazon.com ↗ 213 Yi-Lightning 01.AI 54±1 * api price unknown 16k platform.lingyiwanwu.com ↗ 214 Olmo 3.1 32B Instruct Ai2 54±1 * local ~21GB 66k LM Studio › copy 215 Qwen3 4B Thinking 2507 Alibaba 53±3 * † local ~3.9GB 262k LM Studio › copy 216 Llama 3.1 405B Instruct Meta 53±1 api $2.40/M +local ~160GB 128k docs.aws.amazon.com ↗ 217 GPT-4 Turbo (2024-04-09) OpenAI 53±1 api $15.00/M 128k developers.openai.com ↗ 218 Claude 3.5 Haiku Anthropic 53±1 * comparison only 219 Nemotron-Cascade-14B-Thinking NVIDIA 53±6 * † local ~10GB LM Studio › copy 220 Qwen3-VL 8B Instruct Alibaba 53±3 * † api $0.31/M +local ~6.8GB 256k www.alibabacloud.com ↗ 221 Gemini 1.5 Pro (001) Google 53±1 * comparison only 222 Qwen3 30B-A3B (Apr 2025, hybrid) Alibaba 53±1 api $0.35/M +local ~19GB 33k www.alibabacloud.com ↗ 223 Llama 4 Maverick (402B-A17B) Meta 53±1 api $0.42/M +local ~65GB 1M docs.aws.amazon.com ↗ 224 Seed-OSS 36B Instruct ByteDance Seed 53±5 * † local ~23GB 524k LM Studio › copy 225 DeepSeek-V2.5 (1210) DeepSeek 53±1 * local ~82GB llama.cpp › copy 226 Llama 4 Scout (109B-A17B) Meta 53±1 * api $0.15/M +local ~36GB 328k deepinfra.com ↗ 227 EXAONE 4.0 32B LG AI Research 53±4 * † local ~20GB 131k LM Studio › copy 228 Molmo 2 8B Ai2 53±1 * local ~6.8GB llama.cpp › copy 229 Qwen3-VL 8B Thinking Alibaba 53±3 * † api $0.66/M +local ~6.8GB 256k www.alibabacloud.com ↗ 230 Olmo 3 7B Think Ai2 53±3 local ~5.8GB 66k LM Studio › copy 231 gpt-oss-20b OpenAI 52±1 * api $0.13/M +local ~14GB 131k console.groq.com ↗ 232 GPT-4.1 nano OpenAI 52±1 api $0.17/M 1M developers.openai.com ↗ 233 Athene-V2-Chat 72B Nexusflow 52±1 local ~44GB 33k LM Studio › copy 234 Qwen3-VL 4B Thinking Alibaba 52±3 * † local ~4.1GB 256k llama.cpp › copy 235 Gemma 3n E4B Google 52±1 * local ~6.2GB 32k llama.cpp › copy 236 GPT-4o mini (2024-07-18) OpenAI 52±1 api $0.26/M 128k developers.openai.com ↗ 237 GPT-4 Turbo Preview (0125) OpenAI 52±1 comparison only 238 Qwen3-VL 4B Instruct Alibaba 52±3 * † local ~4.1GB 256k llama.cpp › copy 239 Mistral Large 2 (2407) Mistral 52±1 local ~45GB 128k llama.cpp › copy 240 Granite 4.0 H Micro 3B IBM 52±5 * † local ~3.4GB 131k LM Studio › copy 241 Yi-Large Preview 01.AI 52±2 * comparison only 242 Llama 3.3 70B Instruct Meta 52±1 api $0.72/M +local ~24GB 128k docs.aws.amazon.com ↗ 243 Nemotron 3 Nano 30B-A3B NVIDIA 52±1 * api $0.087/M +local ~20GB 262k deepinfra.com ↗ 244 Qwen3-VL 30B-A3B Thinking Alibaba 51±3 * † api $0.75/M +local ~21GB 256k www.alibabacloud.com ↗ 245 Athene-70B Nexusflow 51±1 * local ~29GB llama.cpp › copy 246 Olmo 3 32B Think Ai2 51±1 local ~21GB 66k LM Studio › copy 247 GPT-4 Turbo Preview (1106) OpenAI 51±1 comparison only 248 Claude 3 Opus Anthropic 51±1 comparison only 249 Gemini 1.5 Flash (002) Google 51±1 * comparison only 250 Qwen2.5 72B Instruct Alibaba 51±1 api $0.37/M +local ~30GB 33k deepinfra.com ↗ 251 Llama 3.1 Nemotron 70B Instruct NVIDIA 51±1 local ~43GB 128k LM Studio › copy 252 DeepSeek-V2.5 DeepSeek 51±1 * local ~151GB 164k Ollama › copy 253 Granite 4.1 8B IBM 51±1 * api $0.11/M +local ~7GB 131k replicate.com ↗ 254 Gemma 2 9B IT SimPO Princeton NLP 51±1 * local ~7.6GB llama.cpp › copy 255 Mistral Large 2 (2411) Mistral 51±1 * local ~78GB 128k llama.cpp › copy 256 Olmo 3 7B Instruct Ai2 50±3 local ~5.8GB 66k LM Studio › copy 257 Magistral Medium 1.0 (2506) Mistral 50±1 * comparison only 258 Gemma 3 4B Google 50±1 api $0.063/M +local ~3.8GB 131k deepinfra.com ↗ 259 Granite 4.1 3B IBM 50±5 * † local ~3.7GB Ollama › copy 260 Mistral Small 3.1 24B (2503) Mistral 50±1 * local ~17GB 128k llama.cpp › copy 261 Granite 4.0 Micro 3B IBM 50±5 * † local ~3.5GB 131k LM Studio › copy 262 Command R7B (12-2024) Cohere 49±3 * local ~6.2GB 128k LM Studio › copy 263 Flan-T5 XXL Google 49±15 * local ~49GB how to run › copy 264 Yi-Large 01.AI 49±2 * comparison only 265 Qwen2.5 32B Instruct Alibaba 49±2 local ~21GB 131k LM Studio › copy 266 C Llama-3-Instruct-8B-SimPO-ExPO Chujie Zheng (ExPO) 49±2 * local ~6.6GB llama.cpp › copy 267 Granite 4.2 3B IBM 49±1 api $0.052/M +local ~3.7GB 131k deepinfra.com ↗ 268 Granite 4.2 8B IBM 49±1 * api $0.11/M +local ~6.6GB 131k wandb.ai ↗ 269 Olmo 3.1 32B Think Ai2 49±1 local ~21GB 66k LM Studio › copy 270 Llama 3.1 Tulu 3 70B DPO Ai2 49±4 * † local ~22GB 131k llama.cpp › copy 271 Granite 4.0 H Small (32B-A9B) IBM 49±1 api $0.11/M +local ~21GB 131k replicate.com ↗ 272 Nova Pro Amazon 49±1 * api $1.40/M 300k docs.aws.amazon.com ↗ 273 Jamba 1.5 Large AI21 Labs 49±1 local ~839GB how to run › copy 274 Llama-3-Instruct-8B-SimPO Princeton NLP 49±2 * local ~6.6GB llama.cpp › copy 275 Granite 4.0 H Tiny (7B-A1B) IBM 49±4 * † local ~5.6GB 131k LM Studio › copy 276 Gemma 2 27B IT Google 48±1 local ~18GB 8k LM Studio › copy 277 Granite 4.0 H 1B IBM 48±4 local ~2.3GB 131k LM Studio › copy 278 Llama 3.1 70B Instruct Meta 48±1 api $0.72/M +local ~27GB 128k docs.aws.amazon.com ↗ 279 Gemini 1.5 Flash (001) Google 48±1 * comparison only 280 Llama 3.1 Tulu 3 70B Ai2 48±1 local ~43GB 131k LM Studio › copy 281 Llama 3.1 Nemotron 51B Instruct NVIDIA 48±1 * local ~34GB llama.cpp › copy 282 s1.1 32B Simple Scaling 48±4 * local ~22GB 33k LM Studio › copy 283 Mellum2 12B-A2.5B Instruct JetBrains 48±4 * † local ~8.6GB 131k LM Studio › copy 284 LFM2 8B-A1B Liquid AI 48±4 * † comparison only 285 LFM2 2.6B Liquid AI 48±6 * † local ~3GB 33k LM Studio › copy 286 Qwen3 4B Alibaba 47±2 local ~3.7GB 33k LM Studio › copy 287 Ministral 3B (2410) Mistral 47±6 * † comparison only 288 Granite 4.0 1B IBM 47±3 local ~2.4GB 128k LM Studio › copy 289 OLMo 2 13B Instruct (1124) Allen Institute for AI 47±3 * † local ~9.6GB 4k LM Studio › copy 290 Qwen3.5 2B Alibaba 47±3 local ~2.9GB 262k llama.cpp › copy 291 Qwen2.5 14B Instruct Alibaba 47±3 local ~10GB 131k LM Studio › copy 292 Nemotron-4 340B Instruct NVIDIA 47±1 * comparison only 293 GLM-4 (0116) Z.ai 47±2 * comparison only 294 GPT-4 (0314) OpenAI 47±1 comparison only 295 Command R Plus (08-2024) Cohere 47±1 * api $4.38/M +local ~63GB 128k docs.cohere.com ↗ 296 Mellum2 12B-A2.5B Thinking JetBrains 47±3 * † local ~8.6GB 131k LM Studio › copy 297 GLM-4 (0520) Z.ai 47±1 comparison only 298 Mistral Small 3 24B (2501) Mistral 47±1 * local ~16GB 32k LM Studio › copy 299 Qwen3-VL 2B Thinking Alibaba 47±3 * † local ~2.7GB 256k llama.cpp › copy 300 Claude 3 Sonnet Anthropic 46±1 comparison only 301 Reka Core (2024-05-01) Reka AI 46±2 * comparison only 302 Qwen2.5 Coder 32B Instruct Alibaba 46±1 * api $0.74/M +local ~21GB 131k developers.cloudflare.com ↗ 303 Aya Expanse 32B Cohere 46±1 * api $0.75/M +local ~22GB 128k docs.cohere.com ↗ 304 North Micro Vision Instruct (2.4B) Cohere 46±8 * † local ~3.8GB 128k how to run › copy 305 Mistral Small 4 (119B-A6.5B) Mistral 46±7 * † api $0.26/M +local ~40GB 262k docs.mistral.ai ↗ 306 Gemma 2 9B IT Google 46±1 local ~7GB 8k LM Studio › copy 307 Llama 3 70B Instruct Meta 46±1 local ~24GB 8k llama.cpp › copy 308 DeepSeek-Coder-V2 Instruct (0614) DeepSeek 46±1 local ~92GB llama.cpp › copy 309 Qwen2.5 7B Instruct Alibaba 45±2 api $0.30/M +local ~6GB 131k www.together.ai ↗ 310 Claude 3 Haiku Anthropic 45±1 comparison only 311 OpenThinker2 32B Open Thoughts 45±5 * local ~21GB 33k LM Studio › copy 312 GPT-4 (0613) OpenAI 45±1 api $37.50/M 8k developers.openai.com ↗ 313 Qwen2 72B Instruct Alibaba 45±1 local ~33GB 131k llama.cpp › copy 314 Nova Lite Amazon 45±1 * api $0.10/M 300k docs.aws.amazon.com ↗ 315 Granite 3.3 8B Instruct IBM 45±4 * † local ~6.3GB 128k LM Studio › copy 316 LFM2 1.2B Liquid AI 45±4 * † local ~2.2GB 33k LM Studio › copy 317 Gemini 1.5 Flash-8B (001) Google 45±1 * comparison only 318 Command R Plus (04-2024) Cohere 44±1 local ~43GB 128k llama.cpp › copy 319 Phi-4 14B Microsoft 44±1 api $0.087/M +local ~10GB 16k deepinfra.com ↗ 320 OLMo 2 32B Instruct (0325) Ai2 44±1 local ~21GB LM Studio › copy 321 Granite 3.2 8B Instruct IBM 44±4 * † local ~6.6GB 131k llama.cpp › copy 322 EXAONE 3.5 2.4B Instruct LG AI Research 44±3 * † local ~3GB 33k LM Studio › copy 323 Qwen3 1.7B Alibaba 44±2 local ~2.6GB 33k LM Studio › copy 324 Qwen2.5 3B Instruct Alibaba 44±3 * local ~3.3GB 33k LM Studio › copy 325 Qwen2 7B Instruct Alibaba 44±3 * local ~6GB 131k LM Studio › copy 326 Command R (08-2024) Cohere 44±1 * api $0.26/M +local ~21GB 128k docs.cohere.com ↗ 327 Ministral 3 14B Mistral 43±3 * api $0.20/M +local ~9.1GB 262k docs.mistral.ai ↗ 328 LFM2 700M Liquid AI 43±4 * † local ~1.9GB 33k LM Studio › copy 329 Qwen1.5 110B Chat Alibaba 43±1 local ~45GB 32k llama.cpp › copy 330 Qwen3-VL 2B Instruct Alibaba 43±2 * local ~2.7GB 256k llama.cpp › copy 331 Nova Micro Amazon 42±1 * api $0.061/M 128k docs.aws.amazon.com ↗ 332 Mistral Large (2402) Mistral 42±1 comparison only 333 Jamba 1.5 Mini AI21 Labs 42±1 local ~34GB llama.cpp › copy 334 SmolLM3 3B Hugging Face 42±4 * local ~3.3GB 66k LM Studio › copy 335 EXAONE 4.0 1.2B LG AI Research 42±3 * † local ~2.2GB 66k LM Studio › copy 336 Gemini 1.0 Pro (001) Google 42±1 * comparison only 337 Ministral 8B (2410) Mistral 42±1 local ~6.2GB 128k LM Studio › copy 338 Ministral 3 8B Mistral 42±6 * † api $0.15/M +local ~6.5GB 262k docs.mistral.ai ↗ 339 OLMo 2 7B Instruct (1124) Allen Institute for AI 42±4 * † local ~5.8GB 4k LM Studio › copy 340 Qwen1.5 72B Chat Alibaba 41±1 local ~31GB 32k llama.cpp › copy 341 Mixtral 8x22B Instruct v0.1 Mistral 41±1 local ~56GB 64k llama.cpp › copy 342 Aya Expanse 8B Cohere 41±1 * local ~6.2GB 8k LM Studio › copy 343 Reka Flash 21B (2024-02-26) Reka AI 41±1 * comparison only 344 Mistral Medium (2312) Mistral 40±1 comparison only 345 Llama 3.1 Tulu 3 8B Ai2 40±1 local ~6.2GB 131k LM Studio › copy 346 GPT-3.5 Turbo (0125) OpenAI 40±1 api $0.75/M 16k developers.openai.com ↗ 347 Command R (03-2024) Cohere 40±1 local ~24GB 128k llama.cpp › copy 348 Claude Instant 1.2 Anthropic 40±2 * comparison only 349 Claude 2.0 Anthropic 39±1 comparison only 350 Xwin-LM 70B v0.1 Xwin-LM 39±2 * local ~28GB llama.cpp › copy 351 Llama 3 8B Instruct Meta 39±1 local ~6.6GB 8k llama.cpp › copy 352 GPT-3.5 Turbo (0613) OpenAI 39±1 comparison only 353 LFM2 350M Liquid AI 39±4 * † local ~1.7GB 33k LM Studio › copy 354 Zephyr ORPO 141B-A35B v0.1 Hugging Face 39±1 local ~56GB 66k llama.cpp › copy 355 Llama 3.1 8B Instruct Meta 39±1 api $0.22/M +local ~6.2GB 128k docs.aws.amazon.com ↗ 356 Granite 3.1 8B Instruct IBM 39±1 local ~6.6GB 128k llama.cpp › copy 357 Yi 1.5 34B Chat 01.AI 39±1 * local ~22GB 4k LM Studio › copy 358 Claude 2.1 Anthropic 38±1 comparison only 359 Gemma 3 1B Google 38±2 local ~2.2GB 32k LM Studio › copy 360 Qwen3 0.6B Alibaba 38±3 * local ~1.8GB 33k LM Studio › copy 361 Ministral 3 14B Reasoning 2512 Mistral 38±3 * local ~10GB 262k llama.cpp › copy 362 Qwen1.5 32B Chat Alibaba 38±1 * local ~22GB 32k llama.cpp › copy 363 Phi-3-medium-4k-instruct Microsoft 38±1 local ~9.8GB 4k LM Studio › copy 364 Gemma 2 2B IT Google 37±1 * local ~3.1GB 8k LM Studio › copy 365 Phi-3.5-vision-instruct Microsoft 37±8 * local ~10GB how to run › copy 366 Mixtral 8x7B Instruct v0.1 Mistral 37±1 local ~29GB 32k LM Studio › copy 367 GPT-3.5 Turbo (1106) OpenAI 37±1 comparison only 368 DBRX Instruct Databricks 37±1 local ~85GB 32k Ollama › copy 369 InternLM2.5 20B Chat Shanghai AI Laboratory (InternLM) 37±1 * local ~14GB 33k llama.cpp › copy 370 InternLM2 Chat 20B Shanghai AI Laboratory (InternLM) 36±2 * local ~14GB llama.cpp › copy 371 Mistral 7B Instruct v0.3 Mistral 36±2 * local ~5.8GB 32k LM Studio › copy 372 Yi 34B Chat 01.AI 36±1 local ~23GB 4k llama.cpp › copy 373 Qwen1.5 14B Chat Alibaba 36±1 local ~11GB 32k Ollama › copy 374 Granite 3.3 2B Instruct IBM 36±3 * † local ~3GB 128k LM Studio › copy 375 WizardLM 70B V1.0 Microsoft 35±1 local ~32GB llama.cpp › copy 376 OpenChat 3.5 0106 OpenChat 35±1 * local ~6.1GB 8k llama.cpp › copy 377 Tulu 2 DPO 70B Ai2 35±1 local ~32GB llama.cpp › copy 378 Granite 3.1 3B-A800M Instruct IBM 35±5 * † local ~3.6GB 131k llama.cpp › copy 379 Snowflake Arctic Instruct Snowflake 35±1 local ~1007GB how to run › copy 380 Granite 3.0 8B Instruct IBM 35±1 * local ~6.6GB 4k llama.cpp › copy 381 OpenChat 3.5 OpenChat 35±1 * local ~6.1GB 8k llama.cpp › copy 382 DeepSeek LLM 67B Chat DeepSeek 35±1 local ~31GB 4k llama.cpp › copy 383 GPT-3.5 Turbo (0301) OpenAI 35±2 comparison only 384 Gemma 4 E4B Google 35±2 local ~6.9GB 131k LM Studio › copy 385 Gemma 1.1 7B IT Google 35±1 local ~7.1GB 8k llama.cpp › copy 386 Granite 3.1 2B Instruct IBM 35±1 local ~3.1GB 128k llama.cpp › copy 387 Phi-3-small-8k-instruct Microsoft 34±1 local ~17GB how to run › copy 388 Starling-LM 7B beta Nexusflow 34±1 local ~6GB 8k LM Studio › copy 389 Ministral 3 3B Mistral 34±5 * api $0.10/M +local ~3.5GB 262k docs.mistral.ai ↗ 390 Deita 7B v1.0 HKUST NLP 34±2 * local ~32GB how to run › copy 391 Granite 4.0 H 350M IBM 34±4 * † local ~1.7GB 33k LM Studio › copy 392 Vicuna 33B v1.3 LMSYS 34±1 local ~23GB 2k Ollama › copy 393 OpenHermes 2.5 Mistral 7B Nous Research 34±1 local ~6.1GB llama.cpp › copy 394 Granite 3.2 2B Instruct IBM 34±3 * † local ~3GB 131k LM Studio › copy 395 Llama 3.2 3B Instruct Meta 33±1 api $0.12/M +local ~3.4GB 131k developers.cloudflare.com ↗ 396 Llama 2 70B Chat Meta 33±1 local ~32GB 4k llama.cpp › copy 397 OLMo 2 1B Instruct (0425) Allen Institute for AI 33±4 * † local ~2.4GB 4k llama.cpp › copy 398 Starling-LM 7B alpha UC Berkeley (NEST) 33±1 local ~6.1GB 8k llama.cpp › copy 399 OpenThinker3 7B Open Thoughts 33±3 * local ~6GB 33k LM Studio › copy 400 Nous Hermes 2 Mixtral 8x7B DPO Nous Research 33±1 * local ~31GB 33k llama.cpp › copy 401 Gemma 3 270M IT Google 32±5 * † local ~1.7GB 32k LM Studio › copy 402 Granite 3.0 2B Instruct IBM 32±1 * local ~3.2GB 4k llama.cpp › copy 403 SmolLM2 360M Instruct Hugging Face 32±5 * † local ~1.7GB 8k LM Studio › copy 404 QwQ-32B-Preview Alibaba 31±1 * local ~21GB 33k LM Studio › copy 405 WizardLM 13B V1.2 Microsoft 31±1 local ~9.8GB llama.cpp › copy 406 Mistral 7B Instruct v0.2 Mistral 31±1 local ~6GB 32k LM Studio › copy 407 Tulu 2 DPO 13B Allen Institute for AI 31±2 * local ~9.8GB llama.cpp › copy 408 Granite 3.1 1B-A400M Instruct IBM 31±5 * † local ~2.3GB 131k llama.cpp › copy 409 Granite 3.0 3B-A800M Instruct IBM 31±4 * † local ~3.7GB 4k llama.cpp › copy 410 SOLAR 10.7B Instruct v1.0 Upstage 31±1 * local ~8.3GB 4k llama.cpp › copy 411 Qwen3.5 0.8B Alibaba 31±4 * † local ~2GB 262k llama.cpp › copy 412 Dolphin 2.2.1 Mistral 7B Cognitive Computations 31±1 local ~6.1GB llama.cpp › copy 413 Qwen1.5 7B Chat Alibaba 31±1 local ~6.5GB 32k llama.cpp › copy 414 Falcon-180B-Chat TII 30±1 * local ~115GB 2k Ollama › copy 415 Qwen2.5 0.5B Instruct Alibaba 30±3 * local ~1.8GB 33k LM Studio › copy 416 MPT-30B-Chat MosaicML 30±1 comparison only 417 Qwen-14B-Chat Alibaba 30±1 local ~11GB llama.cpp › copy 418 Phi-3-mini-4k-instruct (June 2024 update) Microsoft 30±1 * local ~3.7GB LM Studio › copy 419 Vicuna 13B v1.5 LMSYS 30±1 local ~9.8GB 4k llama.cpp › copy 420 Granite 4.0 350M IBM 30±4 * † local ~1.7GB 32k LM Studio › copy 421 Llama 2 13B Chat Meta 29±1 local ~9.8GB 4k llama.cpp › copy 422 Code Llama 34B Instruct Meta 29±1 * local ~22GB 16k LM Studio › copy 423 Zephyr 7B beta Hugging Face 29±1 local ~6.1GB llama.cpp › copy 424 Tulu 2 DPO 7B Allen Institute for AI 29±2 * local ~5.8GB llama.cpp › copy 425 Phi-3-mini-128k-instruct (Apr 2024) Microsoft 29±1 local ~9.5GB how to run › copy 426 Gemma 7B IT Google 29±1 local ~7.1GB 8k llama.cpp › copy 427 Phi-3-mini-4k-instruct (Apr 2024) Microsoft 29±1 * local ~4GB llama.cpp › copy 428 Zephyr 7B alpha Hugging Face 28±1 local ~6.1GB llama.cpp › copy 429 PaLM 2 Chat (chat-bison@001) Google 28±1 comparison only 430 Gemma 4 E2B Google 28±3 api $0.050/M +local ~5.1GB 131k docs.aws.amazon.com ↗ 431 Llama 3.2 1B Instruct Meta 27±1 api $0.020/M +local ~2.2GB 131k novita.ai ↗ +1 432 Code Llama 70B Instruct Meta 27±1 * local ~28GB 16k llama.cpp › copy 433 Guanaco 33B University of Washington 27±1 local ~70GB how to run › copy 434 Vicuna 7B v1.5 LMSYS 27±1 local ~5.8GB 4k llama.cpp › copy 435 Gemma 1.1 2B IT Google 27±1 local ~3.2GB 8k llama.cpp › copy 436 SmolLM2 1.7B Instruct Hugging Face 27±1 local ~2.6GB 8k LM Studio › copy 437 Granite 3.0 1B-A400M Instruct IBM 26±4 * † local ~2.3GB 4k llama.cpp › copy 438 Qwen2.5 1.5B Instruct Alibaba 26±3 local ~2.4GB 33k LM Studio › copy 439 Mistral 7B Instruct v0.1 Mistral 26±1 * local ~6.1GB 8k llama.cpp › copy 440 Llama 2 7B Chat Meta 25±1 local ~5.8GB 4k llama.cpp › copy 441 Ghost 7B Alpha Ghost X 25±2 * local ~6.1GB llama.cpp › copy 442 Nous-Hermes-13b Nous Research 25±2 * local ~9.8GB 2k llama.cpp › copy 443 Qwen1.5 4B Chat Alibaba 24±1 * local ~4.1GB 32k llama.cpp › copy 444 Gemma 2B IT Google 23±1 local ~3.1GB 8k llama.cpp › copy 445 OLMo 7B Instruct Ai2 21±1 * local ~16GB how to run › copy 446 Koala 13B UC Berkeley (BAIR) 21±1 comparison only 447 Alpaca 13B Stanford CRFM 20±1 comparison only 448 GPT4All-13B-Snoozy Nomic AI 20±1 local ~56GB how to run › copy 449 MPT-7B-Chat MosaicML 20±1 comparison only 450 Falcon 40B Instruct TII 19±1 local ~27GB Ollama › copy 451 ChatGLM3-6B Zhipu AI (THUDM) 19±1 * local ~5.8GB llama.cpp › copy 452 Falcon 7B Instruct TII 18±2 * local ~5.9GB Ollama › copy 453 RWKV-4-Raven 14B RWKV (BlinkDL) 17±1 comparison only 454 ChatGLM2-6B Zhipu AI (THUDM) 16±1 local ~15GB how to run › copy 455 Qwen1.5 1.8B Chat Alibaba 16±5 * local ~2.7GB 33k Ollama › copy 456 Phi-2 (2.7B) Microsoft 14±2 * local ~3.2GB 2k LM Studio › copy 457 OpenAssistant SFT-4 Pythia 12B LAION (OpenAssistant) 14±1 local ~9.5GB llama.cpp › copy 458 GPT-3 text-davinci-001 OpenAI 12±2 * comparison only 459 ChatGLM-6B Zhipu AI (THUDM) 12±1 local ~16GB how to run › copy 460 FastChat-T5 3B LMSYS 10±1 local ~8.5GB how to run › copy 461 Dolly v2 12B Databricks 9±1 comparison only 462 LLaMA 13B Meta 8±1 comparison only 463 StableLM-Tuned-Alpha 7B Stability AI 6±1 local ~6.9GB llama.cpp › copy — ERNIE 4.5 300B-A47B Baidu not yet calibrated local ~97GB 131k llama.cpp › copy — Hermes 3 Llama 3.1 405B Nous Research not yet calibrated local ~114GB 131k llama.cpp › copy — Hermes 3 Llama 3.1 70B Nous Research not yet calibrated local ~44GB 131k Ollama › copy — Hermes 3 Llama 3.1 8B Nous Research not yet calibrated local ~6.6GB 128k llama.cpp › copy — Phi-3.5-mini-instruct Microsoft not yet calibrated local ~3.7GB 128k LM Studio › copy — Phi-4-mini 3.8B Microsoft not yet calibrated api $0.13/M +local ~3.8GB 128k azure.microsoft.com ↗ — Qwen2 0.5B Instruct Alibaba not yet calibrated local ~1.8GB 32k LM Studio › copy — Qwen2 1.5B Instruct Alibaba not yet calibrated local ~2.4GB 32k LM Studio › copy