Open-weight leaderboard
Models whose weights are published, ranked by the Epoch Capabilities Index.
Models whose weights are published, ranked by the Epoch Capabilities Index. Source: Epoch AI. Variants (reasoning effort, batch) are folded into one row.
| # | Model | Capability | Reasoning | Coding | Context | $/M | Weights | Released |
|---|---|---|---|---|---|---|---|---|
| 101 | Phi-2Microsoft | 107.6 | — | — | — | — | Open | 12 Dec 2023 |
| 102 | LLaMA-33BMeta | 107.1 | — | — | — | — | Open | 24 Feb 2023 |
| 103 | Qwen-7BAlibaba (Qwen) | 106.5 | — | — | — | — | Open | 28 Sep 2023 |
| 104 | Llama 2-13BMeta | 105.8 | — | — | — | — | Open | 18 Jul 2023 |
| 105 | StarCoder 2 15BHugging Face | 104.6 | — | — | — | — | Open | 20 Feb 2024 |
| 106 | Yi 6B01.AI | 104.4 | — | — | — | — | Open | 22 Nov 2023 |
| 107 | Falcon-40BTechnology Innovation Institute | 104.0 | — | — | — | — | Open | 25 May 2023 |
| 108 | Baichuan2-13BBaichuan | 102.8 | — | — | — | — | Open | 6 Sep 2023 |
| 109 | Qwen2.5-Coder (1.5B)Alibaba (Qwen) | 102.6 | — | — | — | — | Open | 18 Sep 2024 |
| 110 | Llama 3.2 1BMeta | 102.0 | 23.9 | — | — | — | Open | 24 Sep 2024 |
| 111 | MPT-30BMosaicML | 100.2 | — | — | — | — | Open | 22 Jun 2023 |
| 112 | LLaMA-13BMeta | 100.1 | — | — | — | — | Open | 24 Feb 2023 |
| 113 | Llama 2-7BMeta | 98.5 | — | — | — | — | Open | 18 Jul 2023 |
| 114 | LLaMA-7BMeta | 96.1 | — | — | — | — | Open | 24 Feb 2023 |
| 115 | Baichuan 2-7BBaichuan | 95.8 | — | — | — | — | Open | 20 Sep 2023 |
| 116 | DeepSeek Coder 33BDeepSeek | 95.7 | — | — | — | — | Open | 2 Nov 2023 |
| 117 | Falcon-7BTechnology Innovation Institute | 94.5 | — | — | — | — | Open | 24 Apr 2023 |
| 118 | MPT-7BMosaicML | 94.0 | — | — | — | — | Open | 5 May 2023 |
| 119 | Gemma 2BGoogle | 93.6 | — | — | — | — | Open | 21 Feb 2024 |
| 120 | StarCoder 2 7BHugging Face | 92.9 | — | — | — | — | Open | 20 Feb 2024 |
| 121 | XGen-7BSalesforce | 92.8 | — | — | — | — | Open | 27 Jun 2023 |
| 122 | Phi-1.5Microsoft | 90.8 | — | — | — | — | Open | 11 Sep 2023 |
| 123 | Baichuan1-7BBaichuan | 89.8 | — | — | — | — | Open | 1 Jun 2023 |
| 124 | Dolly 2.0-12bDatabricks | 88.9 | — | — | — | — | Open | 11 Apr 2023 |
| 125 | DeepSeek Coder 6.7BDeepSeek | 88.9 | — | — | — | — | Open | 2 Nov 2023 |
| 126 | StarCoder 2 3BHugging Face | 88.0 | — | — | — | — | Open | 22 Feb 2024 |
| 127 | Cerebras-GPT-13BCerebras | 82.4 | — | — | — | — | Open | 20 Mar 2023 |
| 128 | DeepSeek Coder 1.3BDeepSeek | 62.2 | — | — | — | — | Open | 2 Nov 2023 |
— means no published score from that source yet · click a model for every benchmark with its source
New - awaiting independent evaluation
All new models →- Claude Sonnet 5.5Anthropic · 28 Sep 2026 · AA 56 · 1M · $4.00/M
- Qwen3.8 Max PrimeAlibaba (Qwen) · 23 Sep 2026 · 1M · $6.00/M
- GPT-6 SolOpenAI · 22 Sep 2026 · AA 47.5 · 1.05M · $4.00/M
- GPT-6 LunaOpenAI · 22 Sep 2026 · AA 37.3 · 1.05M · $0.20/M
- GPT-6 Sol ProOpenAI · 22 Sep 2026 · 1.05M · $4.00/M
- GPT-6 Luna ProOpenAI · 22 Sep 2026 · 1.05M · $0.20/M
- Claude Opus 5.5Anthropic · 22 Sep 2026 · AA 57.6 · 1M · $8.00/M
- Grok 4.7xAI · 21 Sep 2026 · AA 46.4 · 500K · $3.00/M
Not ranked until an independent evaluator (Epoch AI) publishes scores. We don't use vendor-reported benchmark claims for rankings.
Best AI for coding →
Models ranked on DeepSWE
Best AI for reasoning →
Ranked on GPQA Diamond
Best AI for math →
Ranked on competition math
Best open-weight models →
Weights you can run yourself
Cheapest capable models →
Lowest blended API price
Best AI coding tools →
Apps & agents by popularity
Best AI image generators →
Apps & models
Best AI for research →
Answer engines & deep research