LLM
LLM Database
340 large language models from GPT-2 to today: organization, release date, open or closed weights, overall index and results on 16 benchmarks — filter, sort and compare side by side.
340 models
Tick two to four models to see all their benchmark results side by side.
| Compare | Model | Organization | Released | Access | ECI | Rank | Benchmarks |
|---|---|---|---|---|---|---|---|
| Claude Haiku 5.5 | Anthropic | Oct 7, 2026 | Closed (API or app) | – | – | 3 | |
| Mistral Large 4 | Mistral AI | Oct 6, 2026 | Unknown | – | – | 1 | |
| GPT-6.1 Sol | OpenAI | Sep 29, 2026 | Closed (API or app) | 166.1 | 3 | 5 | |
| Claude Sonnet 5.5 | Anthropic | Sep 28, 2026 | Closed (API or app) | 165.0 | 4 | 3 | |
| GPT-6 Sol | OpenAI | Sep 22, 2026 | Closed (API or app) | 162.7 | 7 | 5 | |
| GPT-6 Luna | OpenAI | Sep 22, 2026 | Closed (API or app) | 156.3 | 24 | 5 | |
| Claude Opus 5.5 | Anthropic | Sep 22, 2026 | Closed (API or app) | 167.3 | 1 | 5 | |
| Grok 4.7 | xAI | Sep 21, 2026 | Closed (API or app) | 153.5 | 41 | 3 | |
| DeepSeek V4.1 Flash | DeepSeek | Sep 9, 2026 | Open weights | 154.9 | 33 | 2 | |
| GPT-6 Astra | OpenAI | Sep 3, 2026 | Closed (API or app) | 166.4 | 2 | 6 | |
| Muse Spark 1.3 | Meta AI | Sep 2, 2026 | Closed (API or app) | 156.8 | 19 | 1 | |
| Gemini 3.8 Flash | Google DeepMind | Sep 2, 2026 | Closed (API or app) | 156.7 | 20 | 6 | |
| Qwen3.8 Max (0902) | Alibaba | Sep 1, 2026 | Closed (API or app) | 155.1 | 31 | 3 | |
| Claude Fable 5.1 | Anthropic | Sep 1, 2026 | Closed (API or app) | 164.7 | 5 | 5 | |
| GLM-5.3-Flash | Z.ai (Zhipu AI) | Aug 20, 2026 | Open weights | 151.9 | 47 | 4 | |
| Qwen 3.8 27B | Alibaba | Aug 14, 2026 | Open weights | 149.4 | 58 | 2 | |
| GLM-5.3 | Z.ai (Zhipu AI) | Aug 14, 2026 | Closed (API or app) | 155.6 | 27 | 3 | |
| Gemini 3.7 Flash | Google DeepMind | Aug 13, 2026 | Closed (API or app) | 157.3 | 16 | 5 | |
| DeepSeek V4 Pro 0813 | DeepSeek | Aug 13, 2026 | Open weights | 155.3 | 29 | 5 | |
| Grok 4.6 | xAI | Aug 12, 2026 | Closed (API or app) | 156.4 | 23 | 5 | |
| Muse Spark 1.2 | Meta AI | Aug 5, 2026 | Closed (API or app) | 154.9 | 32 | 1 | |
| Qwen 3.8 Max | Alibaba | Aug 2, 2026 | Closed (API or app) | 156.4 | 22 | 3 | |
| DeepSeek V4 Flash 0731 | DeepSeek | Jul 31, 2026 | Open weights | 154.5 | 36 | 5 | |
| Qwen3.7 Flash | Alibaba | Jul 27, 2026 | Closed (API or app) | 144.6 | 88 | 2 | |
| Claude Opus 5 | Anthropic | Jul 24, 2026 | Closed (API or app) | 162.8 | 6 | 5 | |
| Gemini 3.6 Flash | Google DeepMind | Jul 21, 2026 | Closed (API or app) | 154.2 | 38 | 5 | |
| Gemini 3.5 Flash-Lite | Google DeepMind | Jul 21, 2026 | Closed (API or app) | 145.1 | 86 | 4 | |
| Kimi K3 | Moonshot | Jul 16, 2026 | Open weights | 157.4 | 15 | 5 | |
| Inkling-Small | Thinking Machines | Jul 15, 2026 | Open weights | 150.2 | 52 | 5 | |
| Inkling | Thinking Machines | Jul 15, 2026 | Open weights | 148.5 | 63 | 5 | |
| Muse Spark 1.1 | Meta AI | Jul 9, 2026 | Closed (API or app) | 154.2 | 37 | 1 | |
| GPT-5.6 Terra | OpenAI | Jul 9, 2026 | Closed (API or app) | 159.6 | 11 | 5 | |
| GPT-5.6 Sol | OpenAI | Jul 9, 2026 | Closed (API or app) | 161.7 | 10 | 5 | |
| GPT-5.6 Luna | OpenAI | Jul 9, 2026 | Closed (API or app) | 156.4 | 21 | 5 | |
| Grok 4.5 | xAI | Jul 8, 2026 | Closed (API or app) | 153.9 | 39 | 5 | |
| Claude Sonnet 5 | Anthropic | Jun 30, 2026 | Closed (API or app) | 156.2 | 26 | 3 | |
| GLM-5.2 | Z.ai (Zhipu AI) | Jun 16, 2026 | Open weights | 151.8 | 49 | 6 | |
| Kimi K2.7 Code | Moonshot | Jun 12, 2026 | Open weights | 150.0 | 55 | 3 | |
| Claude Fable 5 | Anthropic | Jun 9, 2026 | Closed (API or app) | 162.1 | 9 | 5 | |
| Nemotron 3 Ultra | Nvidia | Jun 4, 2026 | Open weights | 146.2 | 77 | 1 | |
| Qwen3.7-Plus | Alibaba | Jun 2, 2026 | Closed (API or app) | 147.4 | 67 | 2 | |
| MiniMax-M3 | MiniMax | Jun 1, 2026 | Open weights | 146.9 | 69 | 1 | |
| Claude Opus 4.8 | Anthropic | May 28, 2026 | Closed (API or app) | 158.2 | 14 | 5 | |
| Qwen3.7-Max | Alibaba | May 19, 2026 | Closed (API or app) | 153.7 | 40 | 4 | |
| Gemini 3.5 Flash | Google DeepMind | May 19, 2026 | Closed (API or app) | 154.5 | 35 | 6 | |
| GPT-5.5 Instant | OpenAI | May 5, 2026 | Closed (API or app) | 142.5 | 103 | 2 | |
| Mistral Medium 3.5 | Mistral AI | Apr 28, 2026 | Open weights | 141.3 | 111 | 0 | |
| Qwen 3.6 Flash | Alibaba | Apr 27, 2026 | Unknown | 143.3 | 97 | 3 | |
| DeepSeek-V4-Pro | DeepSeek | Apr 24, 2026 | Open weights | 149.1 | 61 | 4 | |
| DeepSeek-V4-Flash | DeepSeek | Apr 24, 2026 | Open weights | 146.1 | 78 | 0 | |
| GPT-5.5 Pro | OpenAI | Apr 23, 2026 | Closed (API or app) | 162.1 | 8 | 4 | |
| GPT-5.5 | OpenAI | Apr 23, 2026 | Closed (API or app) | 159.1 | 12 | 7 | |
| Qwen3.6 27B | Alibaba | Apr 22, 2026 | Open weights | 146.5 | 74 | 2 | |
| Qwen 3.6 Max (Preview) | Alibaba | Apr 20, 2026 | Unknown | 149.2 | 60 | 3 | |
| Kimi K2.6 | Moonshot | Apr 20, 2026 | Open weights | 151.1 | 50 | 4 | |
| Grok 4.3 Beta | xAI | Apr 17, 2026 | Closed (API or app) | 149.2 | 59 | 3 | |
| Claude Opus 4.7 | Anthropic | Apr 16, 2026 | Closed (API or app) | 156.2 | 25 | 8 | |
| Qwen 3.6 35B-A3B | Alibaba | Apr 14, 2026 | Open weights | 143.9 | 94 | 3 | |
| Muse Spark | Meta AI | Apr 8, 2026 | Closed (API or app) | 152.0 | 46 | 2 | |
| GLM-5.1 | Z.ai (Zhipu AI) | Apr 7, 2026 | Open weights | 149.8 | 56 | 4 | |
| Claude Mythos Preview | Anthropic | Apr 7, 2026 | Closed (API or app) | – | – | 1 | |
| Gemma 4 31B IT | Google DeepMind | Apr 2, 2026 | Open weights | 142.7 | 100 | 2 | |
| Gemma 4 26B A4B | Google DeepMind | Apr 2, 2026 | Open weights | 141.8 | 107 | 1 | |
| Qwen 3.6 Plus | Alibaba | Mar 31, 2026 | Closed (API or app) | 147.7 | 65 | 4 | |
| MiniMax-M2.7 | MiniMax | Mar 18, 2026 | Open weights | 145.8 | 82 | 1 | |
| GPT-5.4 Nano | OpenAI | Mar 17, 2026 | Closed (API or app) | 145.8 | 81 | 5 | |
| GPT-5.4 Mini | OpenAI | Mar 17, 2026 | Closed (API or app) | 148.8 | 62 | 5 | |
| GPT-5.4 Pro | OpenAI | Mar 5, 2026 | Closed (API or app) | 158.9 | 13 | 6 | |
| GPT-5.4 | OpenAI | Mar 5, 2026 | Closed (API or app) | 156.8 | 18 | 9 | |
| Gemini 3.1 Flash-Lite | Mar 3, 2026 | Closed (API or app) | 144.5 | 89 | 3 | ||
| Qwen 3.5 Flash (hosted 35B-A3B) | Alibaba | Feb 25, 2026 | Unknown | 144.0 | 93 | 3 | |
| Qwen3.5-9B | Alibaba | Feb 24, 2026 | Open weights | 139.5 | 121 | 2 | |
| Qwen3.5-35B-A3B | Alibaba | Feb 24, 2026 | Open weights | 142.5 | 102 | 1 | |
| Gemini 3.1 Pro | Google DeepMind | Feb 19, 2026 | Closed (API or app) | 154.8 | 34 | 9 | |
| Grok 4.20 | xAI | Feb 17, 2026 | Closed (API or app) | 152.0 | 45 | 6 | |
| Claude Sonnet 4.6 | Anthropic | Feb 17, 2026 | Closed (API or app) | 152.2 | 44 | 6 | |
| Qwen 3.5 Plus (hosted 397B-A17B) | Alibaba | Feb 16, 2026 | Unknown | 146.8 | 71 | 2 | |
| Qwen3.5 397B-A17B | Alibaba | Feb 13, 2026 | Open weights | 146.7 | 73 | 2 | |
| MiniMax-M2.5 | MiniMax | Feb 12, 2026 | Open weights | 146.7 | 72 | 3 | |
| Gemini 3 Deep Think | Google DeepMind | Feb 12, 2026 | Closed (API or app) | – | – | 2 | |
| GLM-5 | Z.ai (Zhipu AI) | Feb 11, 2026 | Open weights | 145.8 | 80 | 5 | |
| GPT-5.3 Codex | OpenAI | Feb 5, 2026 | Closed (API or app) | 156.8 | 17 | 3 | |
| Claude Opus 4.6 | Anthropic | Feb 5, 2026 | Closed (API or app) | 155.2 | 30 | 9 | |
| Kimi K2.5 | Moonshot | Jan 27, 2026 | Open weights | 148.0 | 64 | 7 | |
| MiniMax-M2.1 | MiniMax | Dec 23, 2025 | Open weights | – | – | 1 | |
| GLM-4.7 | Z.ai (Zhipu AI) | Dec 22, 2025 | Open weights | 143.5 | 96 | 3 | |
| GPT-5.2 Codex | OpenAI | Dec 18, 2025 | Closed (API or app) | – | – | 1 | |
| Gemini 3 Flash | Google DeepMind | Dec 17, 2025 | Closed (API or app) | 151.8 | 48 | 7 | |
| GPT-5.2 Pro | OpenAI | Dec 11, 2025 | Closed (API or app) | 155.4 | 28 | 3 | |
| GPT-5.2 | OpenAI | Dec 11, 2025 | Closed (API or app) | 153.4 | 42 | 9 | |
| DeepSeek-V3.2 | DeepSeek | Dec 1, 2025 | Open weights | 146.3 | 76 | 5 | |
| Claude Opus 4.5 | Anthropic | Nov 24, 2025 | Closed (API or app) | 150.1 | 53 | 9 | |
| GPT-5.1-Codex-Max | OpenAI | Nov 19, 2025 | Closed (API or app) | – | – | 2 | |
| Gemini 3 Pro | Google DeepMind | Nov 18, 2025 | Closed (API or app) | 152.9 | 43 | 7 | |
| GPT-5.1 | OpenAI | Nov 13, 2025 | Closed (API or app) | 149.6 | 57 | 7 | |
| GPT-5.1-Codex-mini | OpenAI | Nov 12, 2025 | Closed (API or app) | – | – | 1 | |
| GPT-5.1-Codex | OpenAI | Nov 12, 2025 | Closed (API or app) | – | – | 1 | |
| Kimi K2 Thinking | Moonshot | Nov 6, 2025 | Open weights | 146.0 | 79 | 3 | |
| MiniMax-M2 | MiniMax | Oct 27, 2025 | Open weights | – | – | 1 | |
| Claude Haiku 4.5 | Anthropic | Oct 15, 2025 | Closed (API or app) | 142.4 | 105 | 6 | |
| GPT-5 Pro | OpenAI | Oct 7, 2025 | Closed (API or app) | 150.3 | 51 | 4 | |
| GLM-4.6 | Z.ai (Zhipu AI), Tsinghua University | Sep 30, 2025 | Open weights | – | – | 1 | |
| DeepSeek-V3.2-Exp | DeepSeek | Sep 29, 2025 | Open weights | 145.0 | 87 | 1 | |
| Claude Sonnet 4.5 | Anthropic | Sep 29, 2025 | Closed (API or app) | 146.8 | 70 | 10 | |
| Gemini 2.5 Flash (Sep 2025) | Google DeepMind | Sep 25, 2025 | Closed (API or app) | 143.0 | 98 | 1 | |
| Qwen3-Max | Alibaba | Sep 24, 2025 | Closed (API or app) | 142.4 | 104 | 4 | |
| Grok 4 Fast | xAI | Sep 19, 2025 | Closed (API or app) | 144.2 | 91 | 2 | |
| Magistral Small 1.2 | Mistral AI | Sep 18, 2025 | Open weights | 131.4 | 155 | 1 | |
| GPT-5-Codex | OpenAI | Sep 15, 2025 | Closed (API or app) | – | – | 1 | |
| Kimi K2 (Sep 2025) | Moonshot | Sep 5, 2025 | Open weights | – | – | 1 | |
| DeepSeek-V3.1 | DeepSeek | Aug 21, 2025 | Open weights | 139.9 | 119 | 0 | |
| GPT-5 nano | OpenAI | Aug 7, 2025 | Closed (API or app) | 139.4 | 122 | 7 | |
| GPT-5 mini | OpenAI | Aug 7, 2025 | Closed (API or app) | 145.5 | 84 | 9 | |
| GPT-5 | OpenAI | Aug 7, 2025 | Closed (API or app) | 150.0 | 54 | 11 | |
| gpt-oss-20b | OpenAI | Aug 5, 2025 | Open weights | 137.8 | 129 | 2 | |
| gpt-oss-120b | OpenAI | Aug 5, 2025 | Open weights | 139.9 | 118 | 4 | |
| Claude Opus 4.1 | Anthropic | Aug 5, 2025 | Closed (API or app) | 144.1 | 92 | 6 | |
| GLM-4.5 | Z.ai (Zhipu AI), Tsinghua University | Aug 3, 2025 | Open weights | – | – | 1 | |
| Qwen3-Coder-480B-A35B | Alibaba | Jul 31, 2025 | Open weights | – | – | 1 | |
| Qwen3-30B-A3B-Thinking (Jul 2025) | Alibaba | Jul 30, 2025 | Open weights | 139.6 | 120 | 1 | |
| Qwen3-30B-A3B-Instruct (Jul 2025) | Alibaba | Jul 29, 2025 | Open weights | 137.4 | 132 | 1 | |
| Qwen3-235B-A22B-Thinking (Jul 2025) | Alibaba | Jul 25, 2025 | Open weights | 143.8 | 95 | 2 | |
| Qwen3-235B-A22B-Instruct (Jul 2025) | Alibaba | Jul 25, 2025 | Open weights | 138.9 | 125 | 3 | |
| GLM-4.5-Air | Z.ai (Zhipu AI), Tsinghua University | Jul 20, 2025 | Open weights | – | – | 1 | |
| Kimi K2 (Jul 2025) | Moonshot | Jul 12, 2025 | Open weights | 140.1 | 116 | 2 | |
| Grok 4 | xAI | Jul 9, 2025 | Closed (API or app) | 146.4 | 75 | 6 | |
| Mistral Small 3.2 | Mistral AI | Jun 20, 2025 | Open weights | 131.7 | 154 | 1 | |
| Gemini 2.5 Flash-Lite (Jun 2025) | Google DeepMind | Jun 17, 2025 | Closed (API or app) | 133.9 | 147 | 0 | |
| Gemini 2.5 Flash (Jun 2025) | Google DeepMind | Jun 17, 2025 | Closed (API or app) | 140.8 | 113 | 1 | |
| o3-pro | OpenAI | Jun 10, 2025 | Closed (API or app) | 147.4 | 66 | 3 | |
| Magistral Small 1.0 | Mistral AI | Jun 10, 2025 | Open weights | 133.2 | 149 | 3 | |
| Magistral Medium 1.1 | Mistral AI | Jun 10, 2025 | Closed (API or app) | – | – | 2 | |
| Gemini 2.5 Pro (Jun 2025) | Google DeepMind | Jun 5, 2025 | Closed (API or app) | 145.3 | 85 | 9 | |
| DeepSeek-R1 (May 2025) | DeepSeek | May 28, 2025 | Open weights | 141.3 | 110 | 6 | |
| Claude Sonnet 4 | Anthropic | May 22, 2025 | Closed (API or app) | 141.7 | 108 | 7 | |
| Claude Opus 4 | Anthropic | May 22, 2025 | Closed (API or app) | 142.7 | 99 | 8 | |
| Gemini 2.5 Flash (May 2025) | Google DeepMind | May 20, 2025 | Closed (API or app) | 141.5 | 109 | 4 | |
| Mistral Medium 3 | Mistral AI | May 7, 2025 | Closed (API or app) | 134.1 | 146 | 3 | |
| Gemini 2.5 Pro (May 2025) | Google DeepMind | May 6, 2025 | Closed (API or app) | 142.5 | 101 | 4 | |
| Qwen3-4B | Alibaba | Apr 29, 2025 | Open weights | – | – | 1 | |
| Qwen3-1.7B | Alibaba | Apr 29, 2025 | Open weights | – | – | 1 | |
| Qwen3-8B | Alibaba | Apr 28, 2025 | Open weights | 136.2 | 136 | 1 | |
| Qwen3-32B | Alibaba | Apr 28, 2025 | Open weights | 138.5 | 126 | 2 | |
| Qwen3-30B-A3B | Alibaba | Apr 28, 2025 | Open weights | 136.2 | 135 | 1 | |
| Qwen3-235B-A22B | Alibaba | Apr 28, 2025 | Open weights | 139.3 | 123 | 3 | |
| Qwen3-14B | Alibaba | Apr 28, 2025 | Open weights | 138.2 | 128 | 1 | |
| Gemini 2.5 Flash (Apr 2025) | Google DeepMind | Apr 17, 2025 | Closed (API or app) | 140.0 | 117 | 3 | |
| o4-mini | OpenAI | Apr 16, 2025 | Closed (API or app) | 145.6 | 83 | 9 | |
| o3 | OpenAI | Apr 16, 2025 | Closed (API or app) | 146.9 | 68 | 10 | |
| GPT-4.1 nano | OpenAI | Apr 14, 2025 | Closed (API or app) | 129.6 | 161 | 6 | |
| GPT-4.1 mini | OpenAI | Apr 14, 2025 | Closed (API or app) | 135.0 | 142 | 7 | |
| GPT-4.1 | OpenAI | Apr 14, 2025 | Closed (API or app) | 136.8 | 133 | 9 | |
| Grok-3 mini | xAI | Apr 9, 2025 | Closed (API or app) | 140.3 | 115 | 5 | |
| Grok 3 | xAI | Apr 9, 2025 | Closed (API or app) | 138.3 | 127 | 5 | |
| QWQ-Plus | Alibaba | Apr 8, 2025 | Closed (API or app) | – | – | 1 | |
| Llama 4 Scout | Meta AI | Apr 5, 2025 | Open weights | 129.6 | 160 | 4 | |
| Llama 4 Maverick | Meta AI | Apr 5, 2025 | Open weights | 132.2 | 152 | 6 | |
| GPT-4o (Mar 2025) | OpenAI | Mar 27, 2025 | Closed (API or app) | – | – | 1 | |
| Gemini 2.5 Pro (Mar 2025) | Google DeepMind | Mar 25, 2025 | Closed (API or app) | 144.2 | 90 | 5 | |
| DeepSeek-V3 (Mar 2025) | DeepSeek | Mar 24, 2025 | Open weights | 135.9 | 137 | 4 | |
| o1-pro | OpenAI | Mar 19, 2025 | Closed (API or app) | – | – | 2 | |
| Mistral Small 3.1 | Mistral AI | Mar 17, 2025 | Open weights | 127.5 | 171 | 2 | |
| Cohere Command A | Cohere | Mar 13, 2025 | Open weights | – | – | 1 | |
| Gemma 3 4B | Google DeepMind | Mar 12, 2025 | Open weights | 116.0 | 214 | 1 | |
| Gemma 3 1B | Google DeepMind | Mar 12, 2025 | Open weights | – | – | 1 | |
| Gemma 3 12B | Google DeepMind | Mar 12, 2025 | Open weights | 123.5 | 186 | 1 | |
| Gemma 3 27B | Google DeepMind | Mar 11, 2025 | Open weights | 130.0 | 159 | 3 | |
| QwQ-32B | Alibaba | Mar 5, 2025 | Open weights | 137.6 | 130 | 2 | |
| GPT-4.5 | OpenAI | Feb 27, 2025 | Closed (API or app) | 136.7 | 134 | 6 | |
| Claude 3.7 Sonnet | Anthropic | Feb 24, 2025 | Closed (API or app) | 141.2 | 112 | 8 | |
| Gemini 2.0 Pro | Google DeepMind | Feb 5, 2025 | Closed (API or app) | 135.1 | 141 | 3 | |
| Gemini 2.0 Flash (Feb 2025) | Google DeepMind, Google | Feb 5, 2025 | Closed (API or app) | 134.7 | 145 | 3 | |
| o3-mini | OpenAI | Jan 31, 2025 | Closed (API or app) | 140.3 | 114 | 7 | |
| GPT-4o (Jan 2025) | OpenAI | Jan 29, 2025 | Closed (API or app) | – | – | 1 | |
| Qwen2.5-Max | Alibaba | Jan 25, 2025 | Closed (API or app) | 132.5 | 150 | 3 | |
| Qwen Plus (Jan 2025) | Alibaba | Jan 25, 2025 | Closed (API or app) | – | – | 2 | |
| Mistral Small 3 | Mistral AI | Jan 25, 2025 | Open weights | 127.1 | 175 | 2 | |
| Gemini 2.0 Flash Thinking (Jan 2025) | Google DeepMind, Google | Jan 21, 2025 | Closed (API or app) | 135.4 | 140 | 3 | |
| DeepSeek-R1-Distill-Qwen-32B | DeepSeek | Jan 20, 2025 | Open weights | 137.4 | 131 | 1 | |
| DeepSeek-R1-Distill-Qwen-14B | DeepSeek | Jan 20, 2025 | Open weights | 135.4 | 139 | 2 | |
| DeepSeek-R1-Distill-Qwen-1.5B | DeepSeek | Jan 20, 2025 | Open weights | – | – | 1 | |
| DeepSeek-R1-Distill-Llama-70B | DeepSeek | Jan 20, 2025 | Open weights | – | – | 2 | |
| DeepSeek-R1 | DeepSeek | Jan 20, 2025 | Open weights | 139.0 | 124 | 6 | |
| Codestral | Mistral AI | Jan 13, 2025 | Open weights | – | – | 1 | |
| Eurus-2-7B-PRIME | Tsinghua University, University of Illinois Urbana-Champaign (UIUC), Shanghai AI Lab, Peking University, Shanghai Jiao Tong University, CUHK Shenzhen Research Institute | Dec 31, 2024 | Open weights | – | – | 1 | |
| DeepSeek-V3 | DeepSeek | Dec 26, 2024 | Open weights | 132.3 | 151 | 7 | |
| o1 | OpenAI | Dec 17, 2024 | Closed (API or app) | 141.9 | 106 | 8 | |
| Phi-4 | Microsoft Research | Dec 12, 2024 | Open weights | 130.4 | 157 | 3 | |
| Grok-2 (Dec 2024) | xAI | Dec 12, 2024 | Closed (API or app) | 130.5 | 156 | 2 | |
| Llama 3.3 70B | Meta AI | Dec 6, 2024 | Open weights | 127.3 | 172 | 3 | |
| Gemini 2.0 Flash (Dec 2024) | Google DeepMind, Google | Dec 6, 2024 | Closed (API or app) | 134.7 | 144 | 2 | |
| Amazon Nova Pro | Amazon | Dec 3, 2024 | Closed (API or app) | 123.8 | 185 | 2 | |
| Amazon Nova Micro | Amazon | Dec 3, 2024 | Closed (API or app) | – | – | 1 | |
| Amazon Nova Lite | Amazon | Dec 3, 2024 | Closed (API or app) | – | – | 2 | |
| Yi-Lightning | 01.AI | Dec 2, 2024 | Closed (API or app) | – | – | 1 | |
| INTELLECT-1 | Prime Intellect, Hugging Face, Arcee AI | Nov 29, 2024 | Unknown | 100.9 | 239 | 4 | |
| Tulu 3 (Tülu 3) 70B | Allen Institute for AI, University of Washington | Nov 21, 2024 | Open weights | – | – | 2 | |
| Qwen2.5-Coder-32B-Instruct | Alibaba | Nov 21, 2024 | Open weights | – | – | 2 | |
| GPT-4o (Nov 2024) | OpenAI | Nov 20, 2024 | Closed (API or app) | 128.8 | 167 | 8 | |
| Mistral Large 2 (Nov 2024) | Mistral AI | Nov 15, 2024 | Open weights | 128.5 | 169 | 2 | |
| Qwen-Turbo | Alibaba | Nov 1, 2024 | Closed (API or app) | – | – | 2 | |
| Claude 3.5 Sonnet (October 2024) | Anthropic | Oct 22, 2024 | Closed (API or app) | 133.6 | 148 | 6 | |
| Claude 3.5 Haiku | Anthropic | Oct 22, 2024 | Closed (API or app) | 127.2 | 174 | 4 | |
| Ministral 8B | Mistral AI | Oct 16, 2024 | Open weights | – | – | 2 | |
| Ministral 3B | Mistral AI | Oct 16, 2024 | Closed (API or app) | 118.1 | 207 | 2 | |
| Gemini 1.5 Flash 8B | Google DeepMind | Oct 3, 2024 | Closed (API or app) | – | – | 1 | |
| Llama 3.2 90B | Meta AI | Sep 24, 2024 | Open weights | 125.5 | 182 | 3 | |
| Llama 3.2 1B | Meta AI | Sep 24, 2024 | Open weights | 102.0 | 238 | 1 | |
| Llama 3.2 11B | Meta AI | Sep 24, 2024 | Open weights | – | – | 1 | |
| Gemini 1.5 Pro (Sept 2024) | Google DeepMind | Sep 24, 2024 | Closed (API or app) | 131.7 | 153 | 5 | |
| Qwen2.5-7B | Alibaba | Sep 19, 2024 | Open weights | 118.5 | 205 | 2 | |
| Qwen2.5-72B | Alibaba | Sep 19, 2024 | Open weights | 129.0 | 164 | 6 | |
| Qwen2.5-14B | Alibaba | Sep 19, 2024 | Open weights | – | – | 1 | |
| Qwen2.5-Coder-32B | Alibaba | Sep 18, 2024 | Open weights | 119.5 | 199 | 4 | |
| Qwen2.5-Coder (7B) | Alibaba | Sep 18, 2024 | Open weights | 113.1 | 218 | 4 | |
| Qwen2.5-Coder (1.5B) | Alibaba | Sep 18, 2024 | Open weights | 103.0 | 237 | 4 | |
| Qwen2.5-32B | Alibaba | Sep 17, 2024 | Open weights | 128.5 | 168 | 2 | |
| o1-preview | OpenAI | Sep 12, 2024 | Closed (API or app) | 134.8 | 143 | 4 | |
| o1-mini | OpenAI | Sep 12, 2024 | Closed (API or app) | 135.8 | 138 | 5 | |
| DeepSeek-V2.5 (Sep 2024) | DeepSeek | Sep 6, 2024 | Open weights | – | – | 1 | |
| Command R+ | Cohere, Cohere Labs (formerly Cohere for AI) | Aug 30, 2024 | Open weights | 119.3 | 201 | 1 | |
| Gemini 1.5 Flash (Sep 2024) | Google DeepMind | Aug 27, 2024 | Closed (API or app) | 129.4 | 162 | 3 | |
| Phi-3.5-MoE | Microsoft | Aug 17, 2024 | Open weights | – | – | 1 | |
| Phi-3.5-mini | Microsoft | Aug 16, 2024 | Open weights | – | – | 1 | |
| GPT-4o (Aug 2024) | OpenAI | Aug 6, 2024 | Closed (API or app) | 128.8 | 166 | 6 | |
| Mistral Large 2 (Jul 2024) | Mistral AI | Jul 24, 2024 | Open weights | 127.5 | 170 | 3 | |
| Llama 3.1-8B | Meta AI | Jul 23, 2024 | Open weights | 116.6 | 212 | 4 | |
| Llama 3.1-70B | Meta AI | Jul 23, 2024 | Open weights | 125.9 | 181 | 3 | |
| Llama 3.1-405B | Meta AI | Jul 23, 2024 | Open weights | 128.8 | 165 | 5 | |
| Mistral NeMo | Mistral AI | Jul 18, 2024 | Open weights | 118.7 | 202 | 3 | |
| GPT-4o mini | OpenAI | Jul 18, 2024 | Closed (API or app) | 126.6 | 178 | 8 | |
| Gemma 2 9B | Google DeepMind | Jun 24, 2024 | Open weights | 119.8 | 198 | 4 | |
| Gemma 2 27B | Google DeepMind | Jun 24, 2024 | Open weights | 122.1 | 190 | 3 | |
| Hermes 2 Theta Llama-3 70B | Nous Research, Arcee AI | Jun 20, 2024 | Open weights | – | – | 2 | |
| Claude 3.5 Sonnet | Anthropic | Jun 20, 2024 | Closed (API or app) | 130.0 | 158 | 4 | |
| DeepSeek-Coder-V2 236B | DeepSeek | Jun 17, 2024 | Open weights | – | – | 2 | |
| Qwen2-72B | Alibaba | Jun 7, 2024 | Open weights | 125.3 | 183 | 4 | |
| Gemini 1.5 Pro (May 2024) | Google DeepMind | May 14, 2024 | Closed (API or app) | 126.9 | 177 | 3 | |
| Gemini 1.5 Flash (May 2024) | Google DeepMind | May 14, 2024 | Closed (API or app) | 122.6 | 189 | 4 | |
| Yi-Large | 01.AI | May 13, 2024 | Closed (API or app) | – | – | 1 | |
| Yi-1.5-34B | 01.AI | May 13, 2024 | Open weights | – | – | 2 | |
| GPT-4o (May 2024) | OpenAI | May 13, 2024 | Closed (API or app) | 129.0 | 163 | 4 | |
| Falcon 2 11B | Technology Innovation Institute | May 9, 2024 | Open weights | 109.6 | 225 | 4 | |
| DeepSeek-V2 (MoE-236B, May 2024) | DeepSeek | May 7, 2024 | Open weights | 124.8 | 184 | 3 | |
| phi-3-small 7.4B | Microsoft | Apr 23, 2024 | Open weights | 121.8 | 193 | 3 | |
| phi-3-mini 3.8B | Microsoft | Apr 23, 2024 | Open weights | 117.4 | 209 | 3 | |
| phi-3-medium 14B | Microsoft | Apr 23, 2024 | Open weights | 121.2 | 194 | 5 | |
| Llama 3-8B | Meta AI | Apr 18, 2024 | Open weights | 116.5 | 213 | 4 | |
| Llama 3-70B | Meta AI | Apr 18, 2024 | Open weights | 122.9 | 188 | 4 | |
| Mixtral 8x22B | Mistral AI | Apr 17, 2024 | Open weights | 122.0 | 192 | 3 | |
| WizardLM-2 8x22B | Microsoft | Apr 15, 2024 | Open weights | – | – | 2 | |
| GPT-4 Turbo (Apr 2024) | OpenAI | Apr 9, 2024 | Closed (API or app) | 127.2 | 173 | 5 | |
| DBRX | Databricks | Mar 27, 2024 | Open weights | – | – | 2 | |
| Claude 3 Haiku | Anthropic | Mar 7, 2024 | Closed (API or app) | 118.3 | 206 | 4 | |
| Claude 3 Sonnet | Anthropic | Feb 29, 2024 | Closed (API or app) | 120.7 | 195 | 4 | |
| Claude 3 Opus | Anthropic | Feb 29, 2024 | Closed (API or app) | 126.9 | 176 | 6 | |
| Nemotron-4 15B | Nvidia | Feb 26, 2024 | Closed (API or app) | 107.7 | 228 | 4 | |
| Mistral Large | Mistral AI | Feb 26, 2024 | Closed (API or app) | 122.0 | 191 | 3 | |
| StarCoder 2 3B | Hugging Face, ServiceNow, Nvidia, BigCode | Feb 22, 2024 | Open weights | 88.8 | 255 | 3 | |
| Gemma 7B | Google DeepMind | Feb 21, 2024 | Open weights | 112.0 | 222 | 4 | |
| Gemma 2B | Google DeepMind | Feb 21, 2024 | Open weights | 94.2 | 248 | 4 | |
| StarCoder 2 7B | Hugging Face, ServiceNow, Nvidia, BigCode | Feb 20, 2024 | Open weights | 93.6 | 249 | 3 | |
| StarCoder 2 15B | Hugging Face, ServiceNow, Nvidia, BigCode | Feb 20, 2024 | Open weights | 105.0 | 233 | 3 | |
| Gemini 1.5 Pro (Feb 2024) | Google DeepMind | Feb 15, 2024 | Closed (API or app) | – | – | 1 | |
| Qwen1.5-7B | Alibaba | Feb 4, 2024 | Open weights | – | – | 1 | |
| Qwen1.5-72B | Alibaba | Feb 4, 2024 | Open weights | – | – | 1 | |
| Qwen1.5-32B | Alibaba | Feb 4, 2024 | Open weights | – | – | 2 | |
| Qwen1.5-14B | Alibaba | Feb 4, 2024 | Open weights | – | – | 1 | |
| GPT-3.5 Turbo (Jan 2024) | OpenAI | Jan 25, 2024 | Closed (API or app) | 115.7 | 215 | 4 | |
| Gemini 1.0 Pro | Google DeepMind | Dec 13, 2023 | Closed (API or app) | 117.0 | 211 | 3 | |
| Phi-2 | Microsoft | Dec 12, 2023 | Open weights | 107.9 | 227 | 3 | |
| Mixtral 8x7B | Mistral AI | Dec 11, 2023 | Open weights | 118.5 | 204 | 6 | |
| Mistral 7B v0.2 | Mistral AI | Dec 11, 2023 | Open weights | – | – | 2 | |
| DeepSeek LLM 67B | DeepSeek | Nov 29, 2023 | Open weights | 110.5 | 223 | 2 | |
| Claude 2.1 | Anthropic | Nov 21, 2023 | Closed (API or app) | 119.3 | 200 | 2 | |
| GPT-4 Turbo (Nov 2023) | OpenAI | Nov 6, 2023 | Closed (API or app) | 126.5 | 179 | 4 | |
| GPT-3.5 Turbo (Nov 2023) | OpenAI | Nov 6, 2023 | Closed (API or app) | 118.5 | 203 | 4 | |
| Yi-34B | 01.AI | Nov 2, 2023 | Open weights | 117.4 | 208 | 4 | |
| Yi 6B | 01.AI | Nov 2, 2023 | Open weights | 104.8 | 234 | 4 | |
| DeepSeek Coder 6.7B | DeepSeek, Peking University | Nov 2, 2023 | Open weights | 89.6 | 254 | 3 | |
| DeepSeek Coder 33B | DeepSeek, Peking University | Nov 2, 2023 | Open weights | 96.3 | 245 | 3 | |
| DeepSeek Coder 1.3B | DeepSeek, Peking University | Nov 2, 2023 | Open weights | 63.6 | 257 | 3 | |
| Qwen-7B | Alibaba | Sep 28, 2023 | Open weights | 106.8 | 230 | 2 | |
| Mistral 7B v0.3 | Mistral AI | Sep 27, 2023 | Open weights | 109.0 | 226 | 3 | |
| Mistral 7B v0.1 | Mistral AI | Sep 27, 2023 | Open weights | 112.2 | 220 | 4 | |
| Qwen-14B | Alibaba | Sep 24, 2023 | Open weights | 113.0 | 219 | 2 | |
| Baichuan 2-7B | Baichuan | Sep 20, 2023 | Open weights | 96.3 | 244 | 3 | |
| GPT-3.5 Turbo Instruct | OpenAI | Sep 18, 2023 | Closed (API or app) | – | – | 1 | |
| Phi-1.5 | Microsoft | Sep 11, 2023 | Open weights | 91.5 | 251 | 3 | |
| Falcon-180B | Technology Innovation Institute | Sep 6, 2023 | Open weights | 112.1 | 221 | 4 | |
| Baichuan2-13B | Baichuan | Sep 6, 2023 | Open weights | 103.2 | 236 | 3 | |
| Claude Instant | Anthropic | Aug 9, 2023 | Closed (API or app) | 120.3 | 196 | 2 | |
| Stable Beluga 2 | Stability AI | Jul 20, 2023 | Open weights | 117.1 | 210 | 3 | |
| Llama 2-7B | Meta AI | Jul 18, 2023 | Open weights | 99.1 | 242 | 4 | |
| Llama 2-70B | Meta AI | Jul 18, 2023 | Open weights | 113.8 | 216 | 6 | |
| Llama 2-34B | Meta AI | Jul 18, 2023 | Closed (API or app) | 105.2 | 232 | 3 | |
| Llama 2-13B | Meta AI | Jul 18, 2023 | Open weights | 106.2 | 231 | 4 | |
| Claude 2 | Anthropic | Jul 11, 2023 | Closed (API or app) | 120.1 | 197 | 3 | |
| Baichuan 1-13B | Baichuan | Jul 11, 2023 | Open weights | – | – | 2 | |
| XGen-7B | Salesforce | Jun 27, 2023 | Open weights | 93.4 | 250 | 3 | |
| MPT-30B | MosaicML | Jun 22, 2023 | Open weights | 100.7 | 240 | 3 | |
| Inflection-1 | Inflection AI | Jun 22, 2023 | Closed (API or app) | – | – | 1 | |
| Vicuna-13B-v1.3 | Large Model Systems Organization, University of California (UC) Berkeley | Jun 18, 2023 | Open weights | – | – | 1 | |
| GPT-4 (Jun 2023) | OpenAI | Jun 13, 2023 | Closed (API or app) | 123.1 | 187 | 4 | |
| GPT-3.5 Turbo (Jun 2023) | OpenAI | Jun 13, 2023 | Closed (API or app) | 113.4 | 217 | 3 | |
| Baichuan1-7B | Baichuan | Jun 1, 2023 | Open weights | 90.5 | 252 | 2 | |
| MPT-7B | MosaicML | May 5, 2023 | Open weights | 94.6 | 247 | 4 | |
| Falcon-7B | Technology Innovation Institute | Apr 24, 2023 | Open weights | 95.1 | 246 | 4 | |
| Claude 1.3 | Anthropic | Apr 18, 2023 | Closed (API or app) | – | – | 1 | |
| Dolly 2.0-12b | Databricks | Apr 11, 2023 | Open weights | 89.7 | 253 | 3 | |
| Cerebras-GPT-13B | Cerebras Systems | Mar 20, 2023 | Open weights | 83.2 | 256 | 3 | |
| Falcon-40B | Technology Innovation Institute | Mar 15, 2023 | Open weights | 104.5 | 235 | 4 | |
| GPT-4 (Mar 2023) | OpenAI | Mar 14, 2023 | Closed (API or app) | 125.9 | 180 | 6 | |
| LLaMA-7B | Meta AI | Feb 24, 2023 | Open weights | 96.7 | 243 | 4 | |
| LLaMA-65B | Meta AI | Feb 24, 2023 | Open weights | 110.2 | 224 | 4 | |
| LLaMA-33B | Meta AI | Feb 24, 2023 | Open weights | 107.4 | 229 | 4 | |
| LLaMA-13B | Meta AI | Feb 24, 2023 | Open weights | 100.6 | 241 | 4 | |
| davinci-003 | OpenAI | Nov 28, 2022 | Unknown | – | – | 2 | |
| BLOOM-176B | Hugging Face, BigScience | Jul 6, 2022 | Open weights | – | – | 2 | |
| OPT-1.3B | Meta AI | May 11, 2022 | Open weights | – | – | 2 | |
| OPT-66B | Meta AI | May 3, 2022 | Open weights | – | – | 2 | |
| OPT-175B | Meta AI | May 2, 2022 | Open weights | – | – | 2 | |
| GPT-NeoX-20B | EleutherAI | Apr 7, 2022 | Open weights | – | – | 2 | |
| PaLM (540B) | Google Research | Apr 4, 2022 | Closed (API or app) | – | – | 4 | |
| Chinchilla | DeepMind | Mar 29, 2022 | Closed (API or app) | – | – | 2 | |
| davinci-002 | OpenAI | Mar 15, 2022 | Closed (API or app) | – | – | 4 | |
| InstructGPT 6B | OpenAI | Jan 27, 2022 | Closed (API or app) | – | – | 2 | |
| InstructGPT 350M | OpenAI | Jan 27, 2022 | Unknown | – | – | 2 | |
| InstructGPT 175B | OpenAI | Jan 27, 2022 | Closed (API or app) | – | – | 3 | |
| InstructGPT 1.3B | OpenAI | Jan 27, 2022 | Closed (API or app) | – | – | 2 | |
| GLaM | Dec 13, 2021 | Closed (API or app) | – | – | 2 | ||
| Gopher (280B) | DeepMind | Dec 8, 2021 | Closed (API or app) | – | – | 3 | |
| Megatron-Turing NLG 530B | Microsoft, Nvidia | Oct 11, 2021 | Closed (API or app) | – | – | 2 | |
| GPT-J-6B | EleutherAI, LAION | Aug 5, 2021 | Open weights | – | – | 3 | |
| GPT-Neo-2.7B | EleutherAI | Mar 30, 2021 | Open weights | – | – | 1 | |
| GPT-3 XL (babbage) | OpenAI | Jun 22, 2020 | Unknown | – | – | 2 | |
| GPT-3 Medium | OpenAI | Jun 22, 2020 | Unknown | – | – | 2 | |
| GPT-3 6.7B | OpenAI | Jun 22, 2020 | Unknown | – | – | 2 | |
| GPT-3 175B (davinci) | OpenAI | May 28, 2020 | Closed (API or app) | – | – | 3 | |
| GPT-2 (1.5B) | OpenAI | Nov 5, 2019 | Open weights | – | – | 3 |
A model is listed if it has a result in one of the 16 benchmarks on our benchmark page or appears in the overall index. “Benchmarks” counts in how many. Data: Epoch AI, retrieved on October 12, 2026, licensed CC BY 4.0; values unchanged. Logos from the organizations' websites.
