whatmodel.sh · find the best text-to-speech models you can run

Best text-to-speech models for a 4GB Mac

A leaderboard of the best text-to-speech models for a Mac with 4GB of memory. The best one that runs on it right now is VoxCPM2, followed by Wayu-Paxa-TTS-Edge and IndexTTS (v1). Models are ranked by one score that combines 102 published benchmarks. Models that run on it show the download that fits and the command to run it.

86 models · 102 benchmarks · updated
Filter by your hardware and budget → ~3GB fast · reset
ram[2][4][8][16][24][32][48][64][96][128][192][256]
[]
GB
gpu[apple silicon][graphics card][unified memory][none]
price[local][$1][$2][$5][$10][$20][$50][any]max per M chars
Filter by task
task[all tasks][voice cloning]
New #1s for your hardware:
orRSS

detecting your OS…

$ terminal

detecting your OS…

Run curl "whatmodel.sh/tts?ram=4&gpu=apple&max=any"to get this list in your terminal (add &format=json for agents).

Score vs release date

#modelscore↓where↓RAM↓speed↓get itsources
#modelscore↓where↓RAM↓speed↓get itsources
4OpenAudio S1 Fish Audio71±8*†api $15.00/M charsdocs.fish.audio ↗Fish Audio S2 Technical Report
5Voxtral TTS (4B) Mistral71±4†api $16.00/M chars~10GBdocs.mistral.ai ↗Voxtral TTS
7Qwen-Audio-3.0-TTS-Plus Alibaba69±2†api $20.00/M charswww.alibabacloud.com ↗Qwen-Audio-3.0-TTS technical report
8Gemini 3.1 Flash TTS Preview Google69±2api $50.00/M charsfal.ai ↗ZONOS2 Technical Report (ZTTS1-Eval results)Building and Evaluating Fixed-Voice Thai TTS from Synthetic Speech (Wayu Research / Paxa Labs / Typhoon; arXiv:2609.03502v1)RW-Voice-EQ Bench (Hume AI)nsanku TTS Benchmark (GhanaNLP community Space)ZTTS1-Eval results snapshot (Zyphra)Arabic TTS Arena (Navid AI) · leaderboard snapshot 2026-09-24+1
11Grok TTS xAI68±3api $15.00/M charsdocs.x.ai ↗The Humanness Index by Vapi · September 2026 public standingsThe Humanness Index by Vapi · June 2026 production exportArabic TTS Arena (Navid AI) · leaderboard snapshot 2026-09-24
13Simba 3.2 Speechify67±3*api $6.00/M charsspeechify.ai ↗The Humanness Index by Vapi · September 2026 public standings
17MiniMax Speech 2.8 Turbo MiniMax66±3*api $60.00/M charsplatform.minimax.io ↗The Humanness Index by Vapi · September 2026 public standings
19MiniMax Speech 2.8 HD MiniMax66±2api $100.00/M charsplatform.minimax.io ↗Qwen-Audio-3.0-TTS technical reportCN-NewsTTS Bench v0.1Preferences of a Voice-First Nation: pairwise human evaluation of TTS in 10 Indian languages (arXiv:2604.21481v2)
21Chirp 3: HD Google65±4*api $30.00/M charscloud.google.com ↗CN-NewsTTS Bench v0.1
22Eleven v3 ElevenLabs65±1api $100.00/M charselevenlabs.io ↗Qwen-Audio-3.0-TTS technical reportZONOS2 Technical Report (ZTTS1-Eval results)The Humanness Index by Vapi · September 2026 public standingsVoxtral TTSThe Humanness Index by Vapi · June 2026 production exportRW-Voice-EQ Bench (Hume AI)+2
23Higgs Audio V3 TTS Boson AI65±3api $15.00/M chars~10GBdocs.boson.ai ↗Higgs Audio v3 comparison tables in SGLang-Omni cookbook (Boson AI contribution)RW-Voice-EQ Bench (Hume AI)RVCBench: Benchmarking Robustness of Voice Cloning Across Modern Audio Generation Models (arXiv:2602.00443v2)Arabic TTS Arena (Navid AI) · leaderboard snapshot 2026-09-24
28VoxCPM2 · mlx-4bit (mlx-audio) OpenBMB64±1local~2.3GBhow to run › UltraEval-Audio (OpenBMB) · TTS replication resultsQwen-Audio-3.0-TTS technical reportZONOS2 Technical Report (ZTTS1-Eval results)nineninesix/gepard-1.0 model card (Seed-TTS-eval benchmark table)ZTTS1-Eval results snapshot (Zyphra)Arabic TTS Arena (Navid AI) · leaderboard snapshot 2026-09-24
29Wayu-Paxa-TTS-Edge · fp32 (wayu-tts package) Wayu Research / Paxa Labs64±4†local~0.3GBhow to run › Building and Evaluating Fixed-Voice Thai TTS from Synthetic Speech (Wayu Research / Paxa Labs / Typhoon; arXiv:2609.03502v1)
30Eleven Turbo v2.5 ElevenLabs63±4*api $50.00/M charselevenlabs.io ↗The Humanness Index by Vapi · June 2026 production export
32Fish Audio S2.1 Pro Fish Audio63±3*api $15.00/M charsdocs.fish.audio ↗The Humanness Index by Vapi · September 2026 public standings
36Fish Audio S2 Pro Fish Audio63±1api $15.00/M chars~11GBdocs.fish.audio ↗UltraEval-Audio (OpenBMB) · TTS replication resultsZONOS2 Technical Report (ZTTS1-Eval results)RW-Voice-EQ Bench (Hume AI)nineninesix/gepard-1.0 model card (Seed-TTS-eval benchmark table)Higgs Audio v3 comparison tables in SGLang-Omni cookbook (Boson AI contribution)ZTTS1-Eval results snapshot (Zyphra)+3
37MiniMax Speech-02-HD MiniMax63±3api $100.00/M charsplatform.minimax.io ↗The Humanness Index by Vapi · September 2026 public standingsEmergentTTS-Eval six-category leaderboard
38Eleven Flash v2.5 ElevenLabs62±2api $50.00/M charselevenlabs.io ↗The Humanness Index by Vapi · September 2026 public standingsVoxtral TTSThe Humanness Index by Vapi · June 2026 production exportRime Alpha TTS Benchmark v1.0.0 · SupportBench and ContentBench paired human preference
39IndexTTS (v1) · fp32 on CPU (index-tts repo CLI `indextts`) IndexTeam (bilibili)62±3local~1.2GBhow to run › DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation (arXiv:2510.12210v2)
40F5-TTS v1 Base · fp32 SWivid (SJTU X-LANCE)62±3local~1.4GBhow to run › DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation (arXiv:2510.12210v2)RVCBench: Benchmarking Robustness of Voice Cloning Across Modern Audio Generation Models (arXiv:2602.00443v2)
41ZipVoice · fp32 (ZipVoice repo) k2-fsa (Xiaomi)62±3local~0.6GBhow to run › OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models (arXiv:2604.00688v3)RVCBench: Benchmarking Robustness of Voice Cloning Across Modern Audio Generation Models (arXiv:2602.00443v2)
43Inworld TTS-1.5 Max Inworld62±3*api $10.00/M charsfal.ai ↗The Humanness Index by Vapi · September 2026 public standingsThe Humanness Index by Vapi · June 2026 production export
44Qwen3-TTS 12Hz 0.6B Base · bf16 (qwen-tts) Alibaba (Qwen)62±2local~2.5GBhow to run › UltraEval-Audio (OpenBMB) · TTS replication resultsQwen/Qwen3-TTS-12Hz-1.7B-Base model cardSGLang-Omni serving cookbooks (SGLang-Omni team measurements)
46Eleven Flash v2 ElevenLabs62±3*api $50.00/M charselevenlabs.io ↗The Humanness Index by Vapi · September 2026 public standingsThe Humanness Index by Vapi · June 2026 production export
47Eleven Turbo v2 ElevenLabs61±3*api $50.00/M charselevenlabs.io ↗The Humanness Index by Vapi · September 2026 public standingsThe Humanness Index by Vapi · June 2026 production export
49Inworld Realtime TTS-2 Inworld61±2api $25.00/M charsreplicate.com ↗ZONOS2 Technical Report (ZTTS1-Eval results)The Humanness Index by Vapi · September 2026 public standingsThe Humanness Index by Vapi · June 2026 production exportRW-Voice-EQ Bench (Hume AI)Fish Audio Drama 3 technical report
50E2 TTS Base (F5-TTS reproduction) · fp32 SWivid (SJTU X-LANCE)60±2local~1.3GBhow to run › DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation (arXiv:2510.12210v2)F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching (arXiv:2410.06885v1)TTSDS2 listening test results (ttsds/listening_test)An Evaluation Framework for TTS Voice Reconstruction (SAP dysarthric speakers; arXiv:2606.21343v1)TTSDS2 multilingual benchmark results (ttsds/leaderboard_data)
51MiniMax Speech-02-Turbo MiniMax60±3*api $60.00/M charsplatform.minimax.io ↗The Humanness Index by Vapi · September 2026 public standings
52TTS-1 OpenAI59±4api $15.00/M charsdevelopers.openai.com ↗RW-Voice-EQ Bench (Hume AI)
55CosyVoice v3 Plus Alibaba Cloud58±4*api $26.00/M charswww.alibabacloud.com ↗CN-NewsTTS Bench v0.1
56Octave TTS (Octave 1) Hume AI58±4api $50.00/M charswww.hume.ai ↗EmergentTTS-Eval six-category leaderboardInstructTTSEval: instruction-following TTS benchmark (arXiv:2506.16381v1)EmergentTTS-Eval v1 paper (arXiv:2505.23009v1) · Table 1 automatic MOS
57Sonic 3 Cartesia58±2api $65.00/M charswww.together.ai ↗The Humanness Index by Vapi · September 2026 public standingsThe Humanness Index by Vapi · June 2026 production exportRime Alpha TTS Benchmark v1.0.0 · SupportBench and ContentBench paired human preferencePreferences of a Voice-First Nation: pairwise human evaluation of TTS in 10 Indian languages (arXiv:2604.21481v2)
60F5-TTS Base (v0) · fp32 SWivid (SJTU X-LANCE)57±2local~1.4GBhow to run › F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching (arXiv:2410.06885v1)TTSDS2 listening test results (ttsds/listening_test)TTSDS2 multilingual benchmark results (ttsds/leaderboard_data)
61Deepgram Aura 2 Deepgram57±3api $30.00/M charsdeepgram.com ↗Rime Alpha TTS Benchmark v1.0.0 · SupportBench and ContentBench paired human preferenceEmergentTTS-Eval six-category leaderboardRW-Voice-EQ Bench (Hume AI)EmergentTTS-Eval v1 paper (arXiv:2505.23009v1) · Table 1 automatic MOS
63TTS-1 HD OpenAI56±7*api $30.00/M charsdevelopers.openai.com ↗RW-Voice-EQ Bench (Hume AI)
64Supertonic 3 · onnx-fp32 (supertonic Python SDK 1.3.x) Supertone55±10*local~0.4GBhow to run › Arabic TTS Arena (Navid AI) · leaderboard snapshot 2026-09-24
68CosyVoice-300M · fp32 (CosyVoice repo) Alibaba (FunAudioLLM)55±3local~2.3GBhow to run › F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching (arXiv:2410.06885v1)VERSA toolkit paper: TTS demonstration (arXiv:2412.17667v2)Amphion MaskGCT README · zero-shot TTS results table
71Lightning v3.1 Smallest.ai53±3*api $17.50/M charssmallest.ai ↗The Humanness Index by Vapi · September 2026 public standingsRW-Voice-EQ Bench (Hume AI)
73LEMAS-TTS (w/ prosody, multilingual_prosody) · official checkpoint (LEMAS-TTS repo, F5-TTS-based) LEMAS Project52±6*†local~1.5GBhow to run › LEMAS multilingual audio suite report
74Kokoro 82M v1.0 · bf16 hexgrad52±3local~0.7GBhow to run › EmergentTTS-Eval six-category leaderboardParadee: Distilling Kokoro-82M into an 8M-Parameter Single-Voice TTS Model (arXiv:2610.06817v1), Table 3 small-model comparisoncarun/tts-bench: intelligibility benchmark of four open TTS engines (published run, 2026-09-10)RW-Voice-EQ Bench (Hume AI)
78Gradium TTS Gradium51±3*api $38.00/M charsdocs.gradium.ai ↗The Humanness Index by Vapi · September 2026 public standingsThe Humanness Index by Vapi · June 2026 production export
79OpenVoice V1 · fp32 (myshell-ai/OpenVoice) MyShell51±15*local~0.3GBhow to run › TTSDS v1 published results
80Eleven Multilingual v2 ElevenLabs50±5api $100.00/M charselevenlabs.io ↗EmergentTTS-Eval six-category leaderboardEmergentTTS-Eval v1 paper (arXiv:2505.23009v1) · Table 1 automatic MOS
84LEMAS-TTS (w/o prosody, multilingual_grl) · official checkpoint (LEMAS-TTS repo, F5-TTS-based) LEMAS Project50±6*†local~1.4GBhow to run › LEMAS multilingual audio suite report
85MMS TTS Amharic · fp32 (transformers VitsModel) Meta50±16*local~0.2GBhow to run › Addis AI Amharic TTS benchmark
86Chatterbox Resemble AI49±5api $25.00/M chars~2.9GB~2×replicate.com ↗EmergentTTS-Eval six-category leaderboardCodecMOS-Accent: listening-test MOS of zero-shot TTS across English accents (arXiv:2603.14328v1)
87Parler-TTS Mini v0.1 · fp32 Hugging Face (Parler-TTS)49±15*local~2.6GBhow to run › TTSDS v1 published results
90SILMA TTS v1 · fp32 checkpoint (silma-tts 1.0.5) SILMA AI48±10*local~2.7GBhow to run › Arabic TTS Arena (Navid AI) · leaderboard snapshot 2026-09-24
93Orpheus TTS 3B 0.1 (finetune-prod) · gguf Q4_K_M (orpheus-cpp 0.0.3) Canopy Labs47±5local~2.4GBhow to run › EmergentTTS-Eval six-category leaderboardEmergentTTS-Eval v1 paper (arXiv:2505.23009v1) · Table 1 automatic MOS
97Piper (en_US lessac medium) · onnx-fp32 (piper-tts 1.8.0) Open Home Foundation (Piper)47±5*local~0.1GBhow to run › Paradee: Distilling Kokoro-82M into an 8M-Parameter Single-Voice TTS Model (arXiv:2610.06817v1), Table 3 small-model comparison
101Amazon Polly Neural Amazon Web Services45±5*api $16.00/M charsaws.amazon.com ↗CN-NewsTTS Bench v0.1
103GPT-SoVITS v2 · fp32 (repo api_v2.py) RVC-Boss44±4local~1.1GBhow to run › TTSDS2 listening test results (ttsds/listening_test)TTSDS2 multilingual benchmark results (ttsds/leaderboard_data)
105MeloTTS English · fp32 (MeloTTS repo CLI) MyShell44±5local~0.7GBhow to run › VERSA toolkit paper: TTS demonstration (arXiv:2412.17667v2)Audio Deepfake Detection in the Age of Advanced Text-to-Speech models (arXiv:2601.20510v1)
107Nabra-82M v0.1 · fp32 (Kokoro KModel, Oddadmix/kokoro fork) oddadmix41±10*local~0.3GBhow to run › Arabic TTS Arena (Navid AI) · leaderboard snapshot 2026-09-24
108EMA Lightning · fp32 (PyTorch) EMA Lightning (canberkkkkkk)41±3*local~0GBhow to run › Antalia-2 Mini model card (cloud0day3/antalia-mini), public Freya-TR-Eval re-run tableEMA Lightning model card (canberkkkkkk/ema-lightning), Benchmarks: Freya-TR-Eval
109OpenAudio S1 Mini Fish Audio41±5api price unknown~3.6GBdocs.fish.audio ↗LEMAS multilingual audio suite reportArabic TTS Arena (Navid AI) · leaderboard snapshot 2026-09-24CodecMOS-Accent: listening-test MOS of zero-shot TTS across English accents (arXiv:2603.14328v1)
110Fish Speech 1.5 · bf16 (fish-speech repo) Fish Audio40±3local~1.5GBhow to run › TTSDS2 listening test results (ttsds/listening_test)TTSDS2 multilingual benchmark results (ttsds/leaderboard_data)
114Magpie TTS Multilingual 357M · f16-gguf (NVIDIA NeMo-Speech.cpp) NVIDIA39±6*local~0.7GB~1×how to run › carun/tts-bench: intelligibility benchmark of four open TTS engines (published run, 2026-09-10)
115Zonos v0.1 Zyphra39±5api price unknown~4.3GBzyphra.com ↗EmergentTTS-Eval six-category leaderboardbalacoon speech_gen_baselines · zero-shot TTS metrics (VCTK, DAPS-celeb)EmergentTTS-Eval v1 paper (arXiv:2505.23009v1) · Table 1 automatic MOS
116Eleven v4 ElevenLabs38±4*api $80.00/M charselevenlabs.io ↗EMA Lightning model card (canberkkkkkk/ema-lightning), Benchmarks: Freya-TR-EvalFish Audio Drama 3 technical report
117Gemini 3.8 Flash TTS Google38±3*api price unknownai.google.dev ↗Antalia-2 Mini model card (cloud0day3/antalia-mini), public Freya-TR-Eval re-run tableEMA Lightning model card (canberkkkkkk/ema-lightning), Benchmarks: Freya-TR-Eval
119Gemini 3.8 Flash-Lite TTS Google38±3*api price unknownai.google.dev ↗Antalia-2 Mini model card (cloud0day3/antalia-mini), public Freya-TR-Eval re-run tableEMA Lightning model card (canberkkkkkk/ema-lightning), Benchmarks: Freya-TR-Eval
123Eleven v4 Turbo ElevenLabs36±4*api $40.00/M charselevenlabs.io ↗EMA Lightning model card (canberkkkkkk/ema-lightning), Benchmarks: Freya-TR-Eval
125Sesame CSM-1B Sesame34±5api $7.00/M chars~6.6GBdeepinfra.com ↗EmergentTTS-Eval six-category leaderboardbalacoon speech_gen_baselines · zero-shot TTS metrics (VCTK, DAPS-celeb)EmergentTTS-Eval v1 paper (arXiv:2505.23009v1) · Table 1 automatic MOSRW-Voice-EQ Bench (Hume AI)
128VALL-E X (Plachtaa open implementation) · fp32 (Plachtaa/VALL-E-X repo) Plachtaa (community)31±4local~1.6GBhow to run › VERSA toolkit paper: TTS demonstration (arXiv:2412.17667v2)ClonEval · Open Voice Cloning Leaderboard (AMU)CodecMOS-Accent: listening-test MOS of zero-shot TTS across English accents (arXiv:2603.14328v1)
129OuteTTS 0.2 500M · fp32 (outetts 0.3.3) OuteAI31±6*local~1.4GBhow to run › ClonEval · Open Voice Cloning Leaderboard (AMU)
131StyleTTS 2 (LibriTTS) · fp32 (styletts2 PyPI package 0.1.6) Yinghao Aaron Li et al. (Columbia University)30±2local~0.9GBhow to run › TTSDS2 listening test results (ttsds/listening_test)ZS-TTS-Evaluation (Edresson Casanova) · zero-shot TTS metrics of XTTS, YourTTS, TorToiSe and StyleTTS 2StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion (arXiv:2409.10058v1)DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors (arXiv:2406.11427v2)An Evaluation Framework for TTS Voice Reconstruction (SAP dysarthric speakers; arXiv:2606.21343v1)RVCBench: Benchmarking Robustness of Voice Cloning Across Modern Audio Generation Models (arXiv:2602.00443v2)+2
132XTTS v2 · fp32 (coqui-tts 0.27.5) Coqui30±2local~1.9GBhow to run › Antalia-2 Mini model card (cloud0day3/antalia-mini), public Freya-TR-Eval re-run tableVoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild (arXiv:2403.16973v3)ZS-TTS-Evaluation (Edresson Casanova) · zero-shot TTS metrics of XTTS, YourTTS, TorToiSe and StyleTTS 2StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion (arXiv:2409.10058v1)DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors (arXiv:2406.11427v2)ClonEval · Open Voice Cloning Leaderboard (AMU)+7
138Piper (tr_TR dfki medium) · onnx-fp32 (piper-tts) Open Home Foundation (Piper)27±4*local~0.1GBhow to run › Antalia-2 Mini model card (cloud0day3/antalia-mini), public Freya-TR-Eval re-run table
139OpenVoice V2 · fp32 (myshell-ai/OpenVoice) MyShell25±3local~0.8GBhow to run › TTSDS2 listening test results (ttsds/listening_test)TTSDS2 multilingual benchmark results (ttsds/leaderboard_data)RVCBench: Benchmarking Robustness of Voice Cloning Across Modern Audio Generation Models (arXiv:2602.00443v2)TTSDS v1 published results
141SpeechT5 TTS · fp32 (transformers) Microsoft23±3local~0.7GBhow to run › TTSDS2 listening test results (ttsds/listening_test)TTSDS2 multilingual benchmark results (ttsds/leaderboard_data)
144MMS TTS Turkish · fp32 (transformers VitsModel) Meta18±4*local~0.2GBhow to run › Antalia-2 Mini model card (cloud0day3/antalia-mini), public Freya-TR-Eval re-run table
145YourTTS · fp32 (coqui-tts) Coqui / Edresson Casanova et al.18±3local~0.4GBhow to run › VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild (arXiv:2403.16973v3)ZS-TTS-Evaluation (Edresson Casanova) · zero-shot TTS metrics of XTTS, YourTTS, TorToiSe and StyleTTS 2DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors (arXiv:2406.11427v2)
—Azure HD 2.5 Microsoftno reviewed resultsapi $22.00/M charsazure.microsoft.com ↗
—Breeze TTS 2 BreezeBlueno reviewed resultsapi $28.00/M chars~3GBbreezeblue.ai ↗
—Eleven v3 Conversational ElevenLabsno reviewed resultsapi $40.00/M charselevenlabs.io ↗
—Kitten TTS Mini 0.8 · fp32 (mlx-audio) KittenMLno reviewed resultslocal~0.3GBhow to run ›
—KittenTTS 2 · ternary-packed LM (kittenml 0.9.3) KittenMLno reviewed resultslocal~2.1GBhow to run ›
—Lightning v3.1 Pro Smallest.aino reviewed resultsapi $19.50/M charssmallest.ai ↗
—LightSpeech + Parallel WaveGAN · fp32 · CPU (microsoft/NeuralSpeech LightSpeech repo, LJSpeech test set) Microsoft NeuralSpeechno reviewed resultslocal~0GBhow to run ›
—MiniMax Speech 2.6 HD MiniMaxno reviewed resultsapi $100.00/M charsplatform.minimax.io ↗
—Octave 2 Hume AIno reviewed resultsapi $25.00/M charswww.hume.ai ↗
—Pocket TTS (English) · fp32 (pocket-tts 3.3.0) Kyutaino reviewed resultslocal~0.2GBhow to run ›
—Polly Generative Amazonno reviewed resultsapi $30.00/M charsaws.amazon.com ↗
—Sonic 3.6 Cartesiano reviewed resultsapi $38.00/M charscartesia.ai ↗
—Voxtral Mini TTS 3 Mistral AIno reviewed resultsapi $13.00/M charsmistral.ai ↗

+ 103 more don't fit your machine or budget · show them

189 of 189 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

86 models · 102 benchmarks · updated