Model database
What the data contains
The bundled SQLite snapshot has 607 configurations, 58 companies, 463 release families and 29 frontier releases from 24 Feb 2023 through 13 Aug 2026.
Scores use Artificial Analysis Intelligence Index v4.1.1 as observed on 15 Aug 2026. Older models are represented by their current rescored values, not necessarily their historical launch-day scores. Of 594 scored configurations, 435 are marked estimated.
The release database is a starting point, not the answer. Capability scores do not capture price, latency, reliability, openness, adoption or willingness to pay.
| DeepSeek V4 Pro 0813 (Reasoning, Max Effort) | DeepSeek | 13 Aug 26 | 53.2 |
| Gemini 3.7 Flash (high) | 13 Aug 26 | 56.0 | |
| Gemini 3.7 Flash (low) | 13 Aug 26 | 50.9 | |
| Gemini 3.7 Flash (medium) | 13 Aug 26 | 53.4 | |
| Qwen3.8 2.4T A95B | Alibaba | 12 Aug 26 | 57.7 |
| K-EXAONE 2.0 0803 | LG AI Research | 12 Aug 26 | 31.0 |
| Motif 3 | Motif Technologies | 12 Aug 26 | 47.4 |
| A.X-K2 | SK Telecom | 12 Aug 26 | 35.0 |
| Grok 4.6 (high) | SpaceXAI | 12 Aug 26 | 60.9 |
| Solar Open2 250B | Upstage | 12 Aug 26 | 37.4 |
| Nemotron 3.5 Lightning | NVIDIA | 11 Aug 26 | 23.6 |
| Muse Glimmer (high) | Meta | 10 Aug 26 | 35.1 |
| Ling 3.0 Tiny | InclusionAI | 6 Aug 26 | 24.5 |
| Solar Pro 4 | Upstage | 6 Aug 26 | 41.6 |
| Muse Spark 1.2 (xhigh) | Meta | 5 Aug 26 | 56.8 |
| Ling 3.0 Flash | InclusionAI | 4 Aug 26 | 37.8 |
| G9v3-39A5B | AI9Stars | 3 Aug 26 | 31.6 |
| Qwen3.8 Max | Alibaba | 3 Aug 26 | 58.1 |
| DeepSeek V4 Flash 0731 (Reasoning, Max Effort) | DeepSeek | 31 Jul 26 | 51.8 |
| Inkling Small | Thinking Machines | 30 Jul 26 | 41.2 |
| Claude Opus 5 (Adaptive Reasoning, Max Effort) | Anthropic | 24 Jul 26 | 63.1 |
| Celeris-1 | Celeris | 24 Jul 26 | 12.4 |
| Agnes 2.5 Pro Alpha | Sapiens AI | 24 Jul 26 | 39.7 |
| G9v3-3B | AI9Stars | 23 Jul 26 | 16.2 |
| Gemini 3.5 Flash-Lite | 21 Jul 26 | 37.4 | |
| Gemini 3.6 Flash (high) | 21 Jul 26 | 51.6 | |
| Kimi K3 (max) | Kimi | 16 Jul 26 | 59.7 |
| Inkling (xhigh) | Thinking Machines | 15 Jul 26 | 42.3 |
| Motif 3 (Beta) | Motif Technologies | 14 Jul 26 | 45.3 |
| JT-4.1 Flash 236B A21B | China Mobile | 9 Jul 26 | 39.9 |
| Muse Spark 1.1 (xhigh) | Meta | 9 Jul 26 | 53.2 |
| GPT-5.6 Luna (max) | OpenAI | 9 Jul 26 | 52.3 |
| GPT-5.6 Sol (max) | OpenAI | 9 Jul 26 | 60.9 |
| GPT-5.6 Terra (max) | OpenAI | 9 Jul 26 | 56.6 |
| Grok 4.5 (high) | SpaceXAI | 8 Jul 26 | 55.8 |
| Hy3 | Tencent | 6 Jul 26 | 42.2 |
| Claude Sonnet 5 (Adaptive Reasoning, Max Effort) | Anthropic | 30 Jun 26 | 55.3 |
| LongCat 2.0 | LongCat | 29 Jun 26 | 34.0 |
| GPT-5.5 Instant (June 2026) | OpenAI | 25 Jun 26 | 29.2 |
| Grok Build 0.1 0616 | SpaceXAI | 16 Jun 26 | 40.7 |
| GLM-5.2 (max) | Z AI | 16 Jun 26 | 52.6 |
| Kimi K2.7 Code | Kimi | 12 Jun 26 | 43.0 |
| DiffusionGemma 26B A4B | 10 Jun 26 | 13.5 | |
| Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) | Anthropic | 9 Jun 26 | 62.1 |
| North Mini Code | Cohere | 9 Jun 26 | 20.2 |
| Nemotron 3 Ultra 550B A55B (Reasoning) | NVIDIA | 4 Jun 26 | 38.3 |
| Gemma 4 12B (Reasoning) | 3 Jun 26 | 22.2 | |
| Nex-N2-Pro | Nex AGI | 2 Jun 26 | 41.7 |
| Qwen3.7 Plus | Alibaba | 1 Jun 26 | 39.4 |
| MiniMax-M3 | MiniMax | 1 Jun 26 | 45.4 |
| Step 3.7 Flash | StepFun | 29 May 26 | 30.9 |
| Claude Opus 4.8 (Adaptive Reasoning, Max Effort) | Anthropic | 28 May 26 | 57.3 |
| LFM2.5-8B-A1B | Liquid AI | 28 May 26 | 8.1 |
| HyperNova 60B 2605 | Multiverse Computing | 26 May 26 | 18.3 |
| MiniCPM5-1B (Reasoning) | OpenBMB | 25 May 26 | 11.9 |
| Command A+ | Cohere | 20 May 26 | 22.8 |
| Qwen3.7 Max | Alibaba | 19 May 26 | 46.7 |
| Gemini 3.5 Flash (high) | 19 May 26 | 52.0 | |
| JT-35B-Flash | China Mobile | 14 May 26 | 29.0 |
| MiniCPM-V 4.6 1.3B | OpenBMB | 11 May 26 | 3.8 |
| Ring-2.6-1T | InclusionAI | 8 May 26 | 31.7 |
| GPT-5.5 Instant (May 2026) | OpenAI | 5 May 26 | 34.3 |
| Grok 4.3 (high) | SpaceXAI | 30 Apr 26 | 37.9 |
| Granite 4.1 30B | IBM | 29 Apr 26 | 8.7 |
| Granite 4.1 3B | IBM | 29 Apr 26 | 4.4 |
| Granite 4.1 8B | IBM | 29 Apr 26 | 6.4 |
| Mistral Medium 3.5 | Mistral | 29 Apr 26 | 30.4 |
| Nemotron 3 Nano Omni 30B A3B Reasoning | NVIDIA | 29 Apr 26 | 15.0 |
| DeepSeek V4 Flash (Reasoning, Max Effort) | DeepSeek | 24 Apr 26 | 42.1 |
| DeepSeek V4 Pro (Reasoning, Max Effort) | DeepSeek | 24 Apr 26 | 45.3 |
| Ling-2.6-1T | InclusionAI | 23 Apr 26 | 26.6 |
| GPT-5.5 (xhigh) | OpenAI | 23 Apr 26 | 56.3 |
| GPT-5.5 Pro (xhigh) | OpenAI | 23 Apr 26 | — |
| Hy3-preview (Reasoning) | Tencent | 23 Apr 26 | 34.4 |
| Qwen3.6 27B (Reasoning) | Alibaba | 22 Apr 26 | 37.7 |
| MiMo-V2.5 | Xiaomi | 22 Apr 26 | 38.0 |
| MiMo-V2.5-Pro | Xiaomi | 22 Apr 26 | 42.9 |
| Ling 2.6 Flash | InclusionAI | 21 Apr 26 | 14.2 |
| Qwen3.6 Max Preview | Alibaba | 20 Apr 26 | 41.1 |
| Kimi K2.6 | Kimi | 20 Apr 26 | 45.1 |
| Qwen3.6 35B A3B (Reasoning) | Alibaba | 16 Apr 26 | 32.1 |
| Claude Opus 4.7 (Adaptive Reasoning, Max Effort) | Anthropic | 16 Apr 26 | 55.0 |
| JT-MINI | China Mobile | 15 Apr 26 | 18.8 |
| EXAONE 4.5 33B | LG AI Research | 9 Apr 26 | 20.5 |
| Muse Spark | Meta | 8 Apr 26 | 44.3 |
| Grok 4.20 0309 v2 (Reasoning) | SpaceXAI | 7 Apr 26 | 38.0 |
| Grok 4.20 0309 v2 (Non-reasoning) | SpaceXAI | 7 Apr 26 | 22.2 |
| GLM-5.1 (Reasoning) | Z AI | 7 Apr 26 | 41.0 |
| Solar Pro 3 | Upstage | 6 Apr 26 | 14.5 |
| Gemma 4 E4B (Reasoning) | 3 Apr 26 | 12.2 | |
| Qwen3.6 Plus | Alibaba | 2 Apr 26 | 40.5 |
| Gemma 4 26B A4B (Reasoning) | 2 Apr 26 | 26.1 | |
| Gemma 4 31B (Reasoning) | 2 Apr 26 | 29.7 | |
| Gemma 4 E2B (Reasoning) | 2 Apr 26 | 9.5 | |
| Step 3.5 Flash 2603 | StepFun | 2 Apr 26 | 26.5 |
| Trinity Large Thinking | Arcee AI | 1 Apr 26 | 18.7 |
| GLM 5V Turbo (Reasoning) | Z AI | 1 Apr 26 | 35.3 |
| Qwen3.5 Omni Flash | Alibaba | 30 Mar 26 | 19.2 |
| Qwen3.5 Omni Plus | Alibaba | 30 Mar 26 | 31.3 |
| KAT Coder Pro V2 | KwaiKAT | 27 Mar 26 | 33.7 |
| MiMo-V2-Omni-0327 | Xiaomi | 27 Mar 26 | 37.3 |
| Nemotron Cascade 2 30B A3B | NVIDIA | 19 Mar 26 | 17.8 |
| MiMo-V2-Omni | Xiaomi | 19 Mar 26 | 35.9 |
| MiniMax-M2.7 | MiniMax | 18 Mar 26 | 38.9 |
| MiMo-V2-Pro | Xiaomi | 18 Mar 26 | 41.4 |
| GPT-5.4 mini (xhigh) | OpenAI | 17 Mar 26 | 40.9 |
| GPT-5.4 nano (xhigh) | OpenAI | 17 Mar 26 | 39.7 |
| Mistral Small 4 (Reasoning) | Mistral | 16 Mar 26 | 19.7 |
| NVIDIA Nemotron 3 Nano 4B | NVIDIA | 16 Mar 26 | 8.6 |
| GLM-5-Turbo | Z AI | 15 Mar 26 | 39.1 |
| Nemotron 3 Super 120B A12B (Reasoning) | NVIDIA | 11 Mar 26 | 25.7 |
| Grok 4.20 0309 (Reasoning) | SpaceXAI | 10 Mar 26 | 37.4 |
| Sarvam 105B (high) | Sarvam | 6 Mar 26 | 11.9 |
| Sarvam 30B (high) | Sarvam | 6 Mar 26 | 6.4 |
| GPT-5.4 (xhigh) | OpenAI | 5 Mar 26 | 53.1 |
| GPT-5.4 Pro (xhigh) | OpenAI | 5 Mar 26 | — |
| Gemini 3.1 Flash-Lite | 3 Mar 26 | 25.6 | |
| Qwen3.5 0.8B (Reasoning) | Alibaba | 2 Mar 26 | 5.2 |
| Qwen3.5 2B (Reasoning) | Alibaba | 2 Mar 26 | 7.4 |
| Qwen3.5 4B (Reasoning) | Alibaba | 2 Mar 26 | 20.4 |
| Qwen3.5 9B (Reasoning) | Alibaba | 2 Mar 26 | 21.8 |
| LFM2 24B A2B | Liquid AI | 25 Feb 26 | 4.6 |
| Qwen3.5 122B A10B (Reasoning) | Alibaba | 24 Feb 26 | 32.8 |
| Qwen3.5 27B (Reasoning) | Alibaba | 24 Feb 26 | 34.6 |
| Qwen3.5 35B A3B (Reasoning) | Alibaba | 24 Feb 26 | 29.9 |
| Mercury 2 | Inception | 20 Feb 26 | 21.9 |
| Gemini 3.1 Pro Preview | 19 Feb 26 | 47.7 | |
| Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) | Anthropic | 17 Feb 26 | 48.4 |
| Tiny Aya Global | Cohere | 17 Feb 26 | 1.0 |
| Qwen3.5 397B A17B (Reasoning) | Alibaba | 16 Feb 26 | 34.3 |
| MiniMax-M2.5 | MiniMax | 12 Feb 26 | 34.5 |
| Nanbeige4.1-3B | Nanbeige | 11 Feb 26 | 11.0 |
| GLM-5 (Reasoning) | Z AI | 11 Feb 26 | 40.6 |
| Tri-21B-think Preview | Trillion Labs | 10 Feb 26 | 13.6 |
| Tri-21B-Think | Trillion Labs | 10 Feb 26 | 12.3 |
| Claude Opus 4.6 (Adaptive Reasoning, Max Effort) | Anthropic | 5 Feb 26 | 44.9 |
| Gemini 3 Deep Think | 5 Feb 26 | — | |
| GPT-5.3 Codex (xhigh) | OpenAI | 5 Feb 26 | 45.5 |
| Qwen3 Coder Next | Alibaba | 3 Feb 26 | 21.3 |
| Step 3.5 Flash | StepFun | 2 Feb 26 | 26.0 |
| LongCat Flash Lite | LongCat | 28 Jan 26 | 17.4 |
| Kimi K2.5 (Reasoning) | Kimi | 27 Jan 26 | 36.0 |
| Qwen3 Max Thinking | Alibaba | 26 Jan 26 | 32.5 |
| LFM2.5-1.2B-Thinking | Liquid AI | 20 Jan 26 | 2.3 |
| Step3 VL 10B | StepFun | 20 Jan 26 | 9.3 |
| GLM-4.7-Flash (Reasoning) | Z AI | 19 Jan 26 | 23.3 |
| Olmo 3.1 32B Instruct | Allen Institute for AI | 13 Jan 26 | 6.2 |
| LFM2.5-1.2B-Instruct | Liquid AI | 5 Jan 26 | 2.3 |
| LFM2.5-VL-1.6B | Liquid AI | 5 Jan 26 | 1.0 |
| Falcon-H1R-7B | TII UAE | 4 Jan 26 | 9.7 |
| K-EXAONE (Reasoning) | LG AI Research | 31 Dec 25 | 22.5 |
| HyperCLOVA X SEED Think (32B) | Naver | 26 Dec 25 | 17.2 |
| MiniMax-M2.1 | MiniMax | 23 Dec 25 | 32.1 |
| GLM-4.7 (Reasoning) | Z AI | 22 Dec 25 | 34.5 |
| Gemini 3 Flash Preview (Reasoning) | 17 Dec 25 | 38.7 | |
| Solar Open 100B (Reasoning) | Upstage | 17 Dec 25 | 15.2 |
| MiMo-V2-Flash (Feb 2026) | Xiaomi | 16 Dec 25 | 34.0 |
| MiMo-V2-Flash (Reasoning) | Xiaomi | 16 Dec 25 | 31.9 |
| K2 Think V2 | MBZUAI Institute of Foundation Models | 15 Dec 25 | 17.4 |
| NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) | NVIDIA | 15 Dec 25 | 14.5 |
| Olmo 3.1 32B Think | Allen Institute for AI | 12 Dec 25 | 7.9 |
| Molmo2-8B | Allen Institute for AI | 11 Dec 25 | 1.6 |
| Mi:dm K 2.5 Pro | Korea Telecom | 11 Dec 25 | 16.6 |
| Mi:dm K 2.5 Pro Preview | Korea Telecom | 11 Dec 25 | — |
| GPT-5.2 (xhigh) | OpenAI | 11 Dec 25 | 43.3 |
| GPT-5.2 Codex (xhigh) | OpenAI | 11 Dec 25 | 41.2 |
| Devstral 2 | Mistral | 9 Dec 25 | 19.2 |
| Devstral Small 2 | Mistral | 9 Dec 25 | 17.7 |
| GLM-4.6V (Reasoning) | Z AI | 8 Dec 25 | 16.9 |
| K2-V2 (high) | MBZUAI Institute of Foundation Models | 5 Dec 25 | 14.2 |
| Motif-2-12.7B-Reasoning | Motif Technologies | 4 Dec 25 | 12.8 |
| Ministral 3 14B | Mistral | 2 Dec 25 | 11.2 |
| Ministral 3 3B | Mistral | 2 Dec 25 | 7.1 |
| Ministral 3 8B | Mistral | 2 Dec 25 | 9.0 |
| Mistral Large 3 | Mistral | 2 Dec 25 | 15.9 |
| DeepSeek V3.2 (Reasoning) | DeepSeek | 1 Dec 25 | 32.8 |
| DeepSeek V3.2 Speciale | DeepSeek | 1 Dec 25 | 22.6 |
| Nova 2.0 Pro Preview (medium) | Amazon | 27 Nov 25 | 22.1 |
| INTELLECT-3 | Prime Intellect | 27 Nov 25 | 15.7 |
| Nova 2.0 Omni (medium) | Amazon | 26 Nov 25 | 21.3 |
| Apriel-v1.6-15B-Thinker | ServiceNow | 25 Nov 25 | 20.8 |
| Claude Opus 4.5 (Reasoning) | Anthropic | 24 Nov 25 | 41.9 |
| Olmo 3 32B Think | Allen Institute for AI | 20 Nov 25 | 6.1 |
| Olmo 3 7B Instruct | Allen Institute for AI | 20 Nov 25 | 2.4 |
| Olmo 3 7B Think | Allen Institute for AI | 20 Nov 25 | 3.6 |
| Grok 4.1 Fast (Reasoning) | SpaceXAI | 19 Nov 25 | 31.3 |
| Cogito v2.1 (Reasoning) | Deep Cogito | 18 Nov 25 | — |
| Gemini 3 Pro Preview (high) | 18 Nov 25 | 40.6 | |
| ERNIE 5.0 Thinking Preview | Baidu | 13 Nov 25 | 22.3 |
| GPT-5.1 (high) | OpenAI | 13 Nov 25 | 37.5 |
| GPT-5.1 Codex (high) | OpenAI | 13 Nov 25 | 35.6 |
| GPT-5.1 Codex mini (high) | OpenAI | 13 Nov 25 | 31.3 |
| Doubao Seed Code | ByteDance Seed | 11 Nov 25 | 26.5 |
| KAT-Coder-Pro V1 | KwaiKAT | 11 Nov 25 | 28.9 |
| Kimi K2 Thinking | Kimi | 6 Nov 25 | 33.5 |
| Qwen3 Max Thinking (Preview) | Alibaba | 3 Nov 25 | 25.5 |
| Kimi Linear 48B A3B Instruct | Kimi | 30 Oct 25 | 8.4 |
| Nova 2.0 Lite (high) | Amazon | 29 Oct 25 | 20.8 |
| Granite 4.0 350M | IBM | 28 Oct 25 | 1.0 |
| Granite 4.0 H 350M | IBM | 28 Oct 25 | 1.0 |
| Granite 4.0 H 1B | IBM | 28 Oct 25 | 2.2 |
| Granite 4.0 1B | IBM | 28 Oct 25 | 1.6 |
| NVIDIA Nemotron Nano 12B v2 VL (Reasoning) | NVIDIA | 28 Oct 25 | 8.8 |
| MiniMax-M2 | MiniMax | 26 Oct 25 | 28.9 |
| Qwen3 VL 32B (Reasoning) | Alibaba | 21 Oct 25 | 18.1 |
| Qwen3 VL 32B Instruct | Alibaba | 21 Oct 25 | 11.0 |
| Claude 4.5 Haiku (Reasoning) | Anthropic | 15 Oct 25 | 29.9 |
| Qwen3 VL 4B (Reasoning) | Alibaba | 14 Oct 25 | 7.7 |
| Qwen3 VL 4B Instruct | Alibaba | 14 Oct 25 | 3.7 |
| Qwen3 VL 8B (Reasoning) | Alibaba | 14 Oct 25 | 10.5 |
| Qwen3 VL 8B Instruct | Alibaba | 14 Oct 25 | 8.2 |
| Ring-1T | InclusionAI | 13 Oct 25 | 16.3 |
| Jamba Reasoning 3B | AI21 Labs | 8 Oct 25 | 3.8 |
| Ling-1T | InclusionAI | 8 Oct 25 | 12.7 |
| LFM2 8B A1B | Liquid AI | 7 Oct 25 | 1.3 |
| Qwen3 VL 30B A3B (Reasoning) | Alibaba | 3 Oct 25 | 13.4 |
| Qwen3 VL 30B A3B Instruct | Alibaba | 3 Oct 25 | 9.9 |
| Apriel-v1.5-15B-Thinker | ServiceNow | 30 Sep 25 | 21.6 |
| GLM-4.6 (Reasoning) | Z AI | 30 Sep 25 | 29.3 |
| Claude 4.5 Sonnet (Reasoning) | Anthropic | 29 Sep 25 | 37.4 |
| DeepSeek V3.2 Exp (Reasoning) | DeepSeek | 29 Sep 25 | 25.9 |
| Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) | 25 Sep 25 | 13.1 | |
| Gemini 2.5 Flash Preview (Sep '25) (Reasoning) | 25 Sep 25 | 24.2 | |
| Qwen3 Max | Alibaba | 23 Sep 25 | 24.5 |
| Qwen3 VL 235B A22B (Reasoning) | Alibaba | 23 Sep 25 | 20.9 |
| Qwen3 VL 235B A22B Instruct | Alibaba | 23 Sep 25 | 14.4 |
| LFM2 2.6B | Liquid AI | 23 Sep 25 | 2.3 |
| GPT-5 Codex (high) | OpenAI | 23 Sep 25 | 37.0 |
| Qwen3 Omni 30B A3B (Reasoning) | Alibaba | 22 Sep 25 | 9.5 |
| Qwen3 Omni 30B A3B Instruct | Alibaba | 22 Sep 25 | 4.8 |
| DeepSeek V3.1 Terminus (Reasoning) | DeepSeek | 22 Sep 25 | 31.1 |
| Granite 4.0 H Small | IBM | 22 Sep 25 | 4.9 |
| Granite 4.0 Micro | IBM | 22 Sep 25 | 2.0 |
| Ring-flash-2.0 | InclusionAI | 19 Sep 25 | 8.0 |
| Grok 4 Fast (Reasoning) | SpaceXAI | 19 Sep 25 | 27.9 |
| Magistral Medium 1.2 | Mistral | 18 Sep 25 | 18.0 |
| Ling-flash-2.0 | InclusionAI | 17 Sep 25 | 9.6 |
| Magistral Small 1.2 | Mistral | 17 Sep 25 | 11.5 |
| Qwen3 Next 80B A3B (Reasoning) | Alibaba | 11 Sep 25 | 16.9 |
| Qwen3 Next 80B A3B Instruct | Alibaba | 11 Sep 25 | 13.8 |
| Ling-mini-2.0 | InclusionAI | 9 Sep 25 | 3.4 |
| Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) | 8 Sep 25 | 15.2 | |
| Qwen3 Max (Preview) | Alibaba | 5 Sep 25 | 19.4 |
| Kimi K2 0905 | Kimi | 5 Sep 25 | 24.0 |
| Apertus 70B Instruct | Swiss AI Initiative | 2 Sep 25 | 2.0 |
| Apertus 8B Instruct | Swiss AI Initiative | 2 Sep 25 | 1.0 |
| Grok Code Fast 1 | SpaceXAI | 28 Aug 25 | 22.0 |
| Hermes 4 - Llama-3.1 405B (Reasoning) | Nous Research | 27 Aug 25 | 8.8 |
| Hermes 4 - Llama-3.1 70B (Reasoning) | Nous Research | 27 Aug 25 | 9.9 |
| DeepSeek V3.1 (Non-reasoning) | DeepSeek | 21 Aug 25 | 21.4 |
| Seed-OSS-36B-Instruct | ByteDance Seed | 20 Aug 25 | 18.5 |
| NVIDIA Nemotron Nano 9B V2 (Reasoning) | NVIDIA | 18 Aug 25 | 8.7 |
| Gemma 3 270M | 14 Aug 25 | 2.0 | |
| Mistral Medium 3.1 | Mistral | 12 Aug 25 | 14.7 |
| GLM-4.5V (Reasoning) | Z AI | 11 Aug 25 | 9.0 |
| GPT-5 (high) | OpenAI | 7 Aug 25 | 35.3 |
| GPT-5 (ChatGPT) | OpenAI | 7 Aug 25 | 15.4 |
| GPT-5 mini (medium) | OpenAI | 7 Aug 25 | 31.6 |
| GPT-5 nano (high) | OpenAI | 7 Aug 25 | 20.1 |
| Qwen3 4B 2507 (Reasoning) | Alibaba | 6 Aug 25 | 11.9 |
| Claude 4.1 Opus (Reasoning) | Anthropic | 5 Aug 25 | 34.5 |
| gpt-oss-120b (high) | OpenAI | 5 Aug 25 | 24.1 |
| gpt-oss-20b (high) | OpenAI | 5 Aug 25 | 15.2 |
| Qwen3 Coder 30B A3B Instruct | Alibaba | 31 Jul 25 | 13.6 |
| Qwen3 30B A3B 2507 (Reasoning) | Alibaba | 30 Jul 25 | 14.6 |
| GLM-4.5 (Reasoning) | Z AI | 28 Jul 25 | 19.7 |
| GLM-4.5-Air | Z AI | 28 Jul 25 | 16.7 |
| Qwen3 235B A22B 2507 (Reasoning) | Alibaba | 25 Jul 25 | 19.9 |
| Llama Nemotron Super 49B v1.5 (Reasoning) | NVIDIA | 25 Jul 25 | 12.4 |
| Qwen3 Coder 480B A35B Instruct | Alibaba | 22 Jul 25 | 18.2 |
| Exaone 4.0 1.2B (Reasoning) | LG AI Research | 15 Jul 25 | 2.5 |
| EXAONE 4.0 32B (Reasoning) | LG AI Research | 15 Jul 25 | 10.5 |
| Kimi K2 | Kimi | 11 Jul 25 | 19.7 |
| LFM2 1.2B | Liquid AI | 10 Jul 25 | 1.0 |
| Devstral Medium | Mistral | 10 Jul 25 | 12.4 |
| Devstral Small (Jul '25) | Mistral | 10 Jul 25 | 9.1 |
| Grok 4 | SpaceXAI | 10 Jul 25 | 34.1 |
| Solar Pro 2 (Reasoning) | Upstage | 9 Jul 25 | 8.8 |
| Jamba 1.7 Large | AI21 Labs | 7 Jul 25 | 5.0 |
| Jamba 1.7 Mini | AI21 Labs | 7 Jul 25 | 2.3 |
| ERNIE 4.5 300B A47B | Baidu | 30 Jun 25 | 8.9 |
| Gemma 3n E2B Instruct | 26 Jun 25 | 1.0 | |
| Gemma 3n E4B Instruct | 26 Jun 25 | 1.0 | |
| Mistral Small 3.2 | Mistral | 20 Jun 25 | 10.7 |
| Gemini 2.5 Flash-Lite (Reasoning) | 17 Jun 25 | 11.4 | |
| MiniMax M1 40k | MiniMax | 17 Jun 25 | 14.5 |
| MiniMax M1 80k | MiniMax | 17 Jun 25 | 17.9 |
| Magistral Medium 1 | Mistral | 10 Jun 25 | 12.5 |
| Magistral Small 1 | Mistral | 10 Jun 25 | 10.6 |
| o3-pro | OpenAI | 10 Jun 25 | 33.3 |
| Gemini 2.5 Pro | 5 Jun 25 | 25.9 | |
| DeepSeek R1 0528 Qwen3 8B | DeepSeek | 29 May 25 | 10.3 |
| DeepSeek R1 0528 (May '25) | DeepSeek | 28 May 25 | 20.4 |
| Sarvam M (Reasoning) | Sarvam | 23 May 25 | 2.6 |
| Claude 4 Opus (Reasoning) | Anthropic | 22 May 25 | 31.7 |
| Claude 4 Sonnet (Reasoning) | Anthropic | 22 May 25 | 29.8 |
| Devstral Small (May '25) | Mistral | 21 May 25 | 11.8 |
| Gemini 2.5 Flash (Reasoning) | 20 May 25 | 20.3 | |
| Gemma 3n E4B Instruct Preview (May '25) | 20 May 25 | 4.2 | |
| Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning) | NVIDIA | 20 May 25 | 8.4 |
| Solar Pro 2 (Preview) (Reasoning) | Upstage | 20 May 25 | 12.5 |
| Mistral Medium 3 | Mistral | 7 May 25 | 12.5 |
| Gemini 2.5 Pro Preview (May' 25) | 6 May 25 | 22.7 | |
| Nova Premier | Amazon | 30 Apr 25 | 12.7 |
| Qwen3 0.6B (Non-reasoning) | Alibaba | 28 Apr 25 | 1.0 |
| Qwen3 1.7B (Reasoning) | Alibaba | 28 Apr 25 | 2.2 |
| Qwen3 14B (Reasoning) | Alibaba | 28 Apr 25 | 10.4 |
| Qwen3 235B A22B (Reasoning) | Alibaba | 28 Apr 25 | 13.5 |
| Qwen3 30B A3B (Reasoning) | Alibaba | 28 Apr 25 | 9.2 |
| Qwen3 32B (Reasoning) | Alibaba | 28 Apr 25 | 11.4 |
| Qwen3 4B (Reasoning) | Alibaba | 28 Apr 25 | 8.2 |
| Qwen3 8B (Reasoning) | Alibaba | 28 Apr 25 | 8.3 |
| Gemini 2.5 Flash Preview (Reasoning) | 17 Apr 25 | 17.7 | |
| Granite 3.3 8B (Non-reasoning) | IBM | 16 Apr 25 | 1.3 |
| o3 | OpenAI | 16 Apr 25 | 31.1 |
| o4-mini (high) | OpenAI | 16 Apr 25 | 26.1 |
| GPT-4.1 | OpenAI | 14 Apr 25 | 19.6 |
| GPT-4.1 mini | OpenAI | 14 Apr 25 | 14.8 |
| GPT-4.1 nano | OpenAI | 14 Apr 25 | 9.6 |
| Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) | NVIDIA | 7 Apr 25 | 8.9 |
| Llama 4 Maverick | Meta | 5 Apr 25 | 14.5 |
| Llama 4 Scout | Meta | 5 Apr 25 | 10.3 |
| GPT-4o (March 2025, chatgpt-4o-latest) | OpenAI | 27 Mar 25 | 12.3 |
| DeepSeek V3 0324 | DeepSeek | 25 Mar 25 | 15.2 |
| Gemini 2.5 Pro Preview (Mar' 25) | 25 Mar 25 | 23.4 | |
| o1-pro | OpenAI | 19 Mar 25 | 19.1 |
| Llama 3.3 Nemotron Super 49B v1 (Reasoning) | NVIDIA | 18 Mar 25 | 12.2 |
| Mistral Small 3.1 | Mistral | 17 Mar 25 | 14.9 |
| OLMo 2 32B | Allen Institute for AI | 13 Mar 25 | 4.7 |
| Command A | Cohere | 13 Mar 25 | 7.5 |
| Gemma 3 1B Instruct | 13 Mar 25 | 1.0 | |
| DeepHermes 3 - Mistral 24B Preview (Non-reasoning) | Nous Research | 13 Mar 25 | 5.0 |
| Gemma 3 12B Instruct | 12 Mar 25 | 5.5 | |
| Gemma 3 27B Instruct | 12 Mar 25 | 7.4 | |
| Gemma 3 4B Instruct | 12 Mar 25 | 1.0 | |
| Reka Flash 3 | Reka AI | 10 Mar 25 | 3.7 |
| Jamba 1.6 Large | AI21 Labs | 6 Mar 25 | 4.7 |
| Jamba 1.6 Mini | AI21 Labs | 6 Mar 25 | 2.1 |
| QwQ 32B | Alibaba | 5 Mar 25 | 13.4 |
| GPT-4.5 (Preview) | OpenAI | 27 Feb 25 | 13.6 |
| Phi-4 Multimodal Instruct | Microsoft | 26 Feb 25 | 4.2 |
| Gemini 2.0 Flash-Lite (Feb '25) | 25 Feb 25 | 8.6 | |
| Claude 3.7 Sonnet (Reasoning) | Anthropic | 24 Feb 25 | 27.6 |
| Grok 3 | SpaceXAI | 19 Feb 25 | 18.6 |
| Grok 3 mini Reasoning (high) | SpaceXAI | 19 Feb 25 | 22.9 |
| Grok 3 Reasoning Beta | SpaceXAI | 19 Feb 25 | 15.2 |
| R1 1776 | Perplexity | 18 Feb 25 | 6.0 |
| Mistral Saba | Mistral | 17 Feb 25 | 6.2 |
| GPT-4o (ChatGPT) | OpenAI | 15 Feb 25 | 8.1 |
| DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning) | Nous Research | 13 Feb 25 | 1.9 |
| Gemini 2.0 Flash (Feb '25) | 5 Feb 25 | 12.2 | |
| Gemini 2.0 Flash-Lite (Preview) | 5 Feb 25 | 8.4 | |
| Gemini 2.0 Pro Experimental (Feb '25) | 5 Feb 25 | 11.8 | |
| o3-mini | OpenAI | 31 Jan 25 | 19.2 |
| Llama 3.1 Tulu3 405B | Allen Institute for AI | 30 Jan 25 | 8.1 |
| Mistral Small 3 | Mistral | 30 Jan 25 | 6.7 |
| Qwen2.5 Max | Alibaba | 28 Jan 25 | 10.1 |
| Sonar Reasoning | Perplexity | 28 Jan 25 | 11.6 |
| Sonar Reasoning Pro | Perplexity | 28 Jan 25 | 18.0 |
| Gemini 2.0 Flash Thinking Experimental (Jan '25) | 21 Jan 25 | 13.3 | |
| Sonar | Perplexity | 21 Jan 25 | 9.4 |
| Sonar Pro | Perplexity | 21 Jan 25 | 9.1 |
| DeepSeek R1 (Jan '25) | DeepSeek | 20 Jan 25 | 18.6 |
| DeepSeek R1 Distill Llama 70B | DeepSeek | 20 Jan 25 | 9.8 |
| DeepSeek R1 Distill Llama 8B | DeepSeek | 20 Jan 25 | 6.2 |
| DeepSeek R1 Distill Qwen 1.5B | DeepSeek | 20 Jan 25 | 3.3 |
| DeepSeek R1 Distill Qwen 14B | DeepSeek | 20 Jan 25 | 9.7 |
| DeepSeek R1 Distill Qwen 32B | DeepSeek | 20 Jan 25 | 11.0 |
| DeepSeek V3 (Dec '24) | DeepSeek | 26 Dec 24 | 14.2 |
| Gemini 2.0 Flash Thinking Experimental (Dec '24) | 19 Dec 24 | 6.4 | |
| GPT-4o mini Realtime (Dec '24) | OpenAI | 17 Dec 24 | — |
| GPT-4o Realtime (Dec '24) | OpenAI | 17 Dec 24 | — |
| Phi-4 | Microsoft | 12 Dec 24 | 4.6 |
| Grok 2 (Dec '24) | SpaceXAI | 12 Dec 24 | 7.8 |
| Gemini 2.0 Flash (experimental) | 11 Dec 24 | 10.6 | |
| DeepSeek-V2.5 (Dec '24) | DeepSeek | 10 Dec 24 | 6.5 |
| Llama 3.3 Instruct 70B | Meta | 6 Dec 24 | 9.3 |
| o1 | OpenAI | 5 Dec 24 | 23.9 |
| Nova Lite | Amazon | 3 Dec 24 | 6.7 |
| Nova Micro | Amazon | 3 Dec 24 | 4.4 |
| Nova Pro | Amazon | 3 Dec 24 | 7.5 |
| QwQ 32B-Preview | Alibaba | 27 Nov 24 | 9.1 |
| OLMo 2 7B | Allen Institute for AI | 26 Nov 24 | 3.5 |
| GPT-4o (Nov '24) | OpenAI | 20 Nov 24 | 11.1 |
| Qwen2.5 Turbo | Alibaba | 18 Nov 24 | 6.0 |
| Mistral Large 2 (Nov '24) | Mistral | 18 Nov 24 | 9.0 |
| Pixtral Large | Mistral | 18 Nov 24 | 8.0 |
| Qwen2.5 Coder Instruct 32B | Alibaba | 11 Nov 24 | 6.9 |
| Claude 3.5 Haiku | Anthropic | 22 Oct 24 | 12.2 |
| Claude 3.5 Sonnet (Oct '24) | Anthropic | 22 Oct 24 | 9.8 |
| Llama 3.1 Nemotron Instruct 70B | NVIDIA | 15 Oct 24 | 7.4 |
| Reka Flash (Sep '24) | Reka AI | 4 Oct 24 | 6.0 |
| Gemini 1.5 Flash-8B | 3 Oct 24 | 5.2 | |
| LFM 40B | Liquid AI | 30 Sep 24 | 3.0 |
| Molmo 7B-D | Allen Institute for AI | 25 Sep 24 | 3.4 |
| Llama 3.2 Instruct 11B (Vision) | Meta | 25 Sep 24 | 3.0 |
| Llama 3.2 Instruct 1B | Meta | 25 Sep 24 | 1.0 |
| Llama 3.2 Instruct 3B | Meta | 25 Sep 24 | 3.9 |
| Llama 3.2 Instruct 90B (Vision) | Meta | 25 Sep 24 | 6.0 |
| Gemini 1.5 Flash (Sep '24) | 24 Sep 24 | 7.8 | |
| Gemini 1.5 Pro (Sep '24) | 24 Sep 24 | 9.9 | |
| Qwen2.5 Instruct 72B | Alibaba | 19 Sep 24 | 9.4 |
| Qwen2.5 Coder Instruct 7B | Alibaba | 19 Sep 24 | 4.1 |
| Qwen2.5 Instruct 32B | Alibaba | 19 Sep 24 | 7.2 |
| Mistral Small (Sep '24) | Mistral | 17 Sep 24 | 4.3 |
| o1-mini | OpenAI | 12 Sep 24 | 14.0 |
| o1-preview | OpenAI | 12 Sep 24 | 17.2 |
| DeepSeek-V2.5 | DeepSeek | 6 Sep 24 | 6.4 |
| Jamba 1.5 Large | AI21 Labs | 22 Aug 24 | 4.8 |
| Jamba 1.5 Mini | AI21 Labs | 22 Aug 24 | 2.3 |
| Hermes 3 - Llama-3.1 70B | Nous Research | 15 Aug 24 | 4.8 |
| Grok Beta | SpaceXAI | 13 Aug 24 | 7.3 |
| GPT-4o (Aug '24) | OpenAI | 6 Aug 24 | 9.4 |
| Mistral Large 2 (Jul '24) | Mistral | 24 Jul 24 | 7.0 |
| Llama 3.1 Instruct 405B | Meta | 23 Jul 24 | 8.3 |
| Llama 3.1 Instruct 70B | Meta | 23 Jul 24 | 6.5 |
| Llama 3.1 Instruct 8B | Meta | 23 Jul 24 | 7.4 |
| GPT-4o mini | OpenAI | 18 Jul 24 | 6.7 |
| Claude 3.5 Sonnet (June '24) | Anthropic | 21 Jun 24 | 8.1 |
| DeepSeek-Coder-V2 | DeepSeek | 17 Jun 24 | 4.7 |
| DeepSeek Coder V2 Lite Instruct | DeepSeek | 17 Jun 24 | 2.7 |
| Qwen2 Instruct 72B | Alibaba | 7 Jun 24 | 5.7 |
| Gemini 1.5 Pro (May '24) | 15 May 24 | 6.1 | |
| Gemini 1.5 Flash (May '24) | 14 May 24 | 4.6 | |
| GPT-4o (May '24) | OpenAI | 13 May 24 | 8.4 |
| DeepSeek-V2-Chat | DeepSeek | 6 May 24 | 3.3 |
| Qwen1.5 Chat 110B | Alibaba | 25 Apr 24 | 3.7 |
| Arctic Instruct | Snowflake | 24 Apr 24 | 3.0 |
| Phi-3 Mini Instruct 3.8B | Microsoft | 23 Apr 24 | 4.3 |
| Llama 3 Instruct 70B | Meta | 18 Apr 24 | 3.1 |
| Llama 3 Instruct 8B | Meta | 18 Apr 24 | 1.0 |
| Mixtral 8x22B Instruct | Mistral | 17 Apr 24 | 4.0 |
| Command-R+ (Apr '24) | Cohere | 4 Apr 24 | 2.6 |
| DBRX Instruct | Databricks | 27 Mar 24 | 2.6 |
| Grok-1 | SpaceXAI | 17 Mar 24 | 5.8 |
| Command-R (Mar '24) | Cohere | 12 Mar 24 | 1.7 |
| Claude 3 Haiku | Anthropic | 4 Mar 24 | 3.5 |
| Claude 3 Opus | Anthropic | 4 Mar 24 | 11.8 |
| Claude 3 Sonnet | Anthropic | 4 Mar 24 | 4.4 |
| Phi-4 Mini Instruct | Microsoft | 26 Feb 24 | 5.7 |
| Mistral Large (Feb '24) | Mistral | 26 Feb 24 | 4.1 |
| Mistral Small (Feb '24) | Mistral | 26 Feb 24 | 3.2 |
| Solar Mini | Upstage | 25 Jan 24 | 6.0 |
| OpenChat 3.5 (1210) | OpenChat | 18 Dec 23 | 2.6 |
| Mistral Medium | Mistral | 11 Dec 23 | 3.2 |
| Mixtral 8x7B Instruct | Mistral | 11 Dec 23 | 2.0 |
| Gemini 1.0 Pro | 6 Dec 23 | 2.7 | |
| Gemini 1.0 Ultra | 6 Dec 23 | 4.3 | |
| Qwen Chat 72B | Alibaba | 30 Nov 23 | 3.0 |
| DeepSeek LLM 67B Chat (V1) | DeepSeek | 29 Nov 23 | 2.6 |
| Claude 2.1 | Anthropic | 21 Nov 23 | 3.5 |
| GPT-4 Turbo | OpenAI | 6 Nov 23 | 7.7 |
| Mistral 7B Instruct | Mistral | 27 Sep 23 | 1.7 |
| Qwen Chat 14B | Alibaba | 25 Sep 23 | 1.7 |
| Llama 2 Chat 13B | Meta | 18 Jul 23 | 2.6 |
| Llama 2 Chat 70B | Meta | 18 Jul 23 | 2.6 |
| Llama 2 Chat 7B | Meta | 18 Jul 23 | 3.9 |
| Claude 2.0 | Anthropic | 11 Jul 23 | 3.3 |
| GPT-3.5 Turbo (0613) | OpenAI | 13 Jun 23 | — |
| PALM-2 | 10 May 23 | 2.8 | |
| Claude Instant | Anthropic | 14 Mar 23 | 1.7 |
| GPT-4 | OpenAI | 14 Mar 23 | 6.8 |
| Llama 65B | Meta | 24 Feb 23 | 1.7 |
No matching releases.