Best for reasoning
Ranked by GPQA Diamond - graduate-level science questions written to be hard to look up.
Ranked by GPQA Diamond - graduate-level science questions written to be hard to look up. Source: Epoch AI. Variants (reasoning effort, batch) are folded into one row.
| # | Model | Capability | Reasoning | Coding | Context | $/M | Weights | Released |
|---|---|---|---|---|---|---|---|---|
| 151 | Tulu 3 (Tülu 3) 70BAllen Institute for AI | — | 46.3 | — | — | — | Open | 21 Nov 2024 |
| 152 | Qwen2.5-32BAlibaba (Qwen) | 128.5 | 46.1 | — | — | — | Open | 17 Sep 2024 |
| 153 | Gemini 1.5 Pro (May 2024)Google | 126.9 | 45.9 | — | — | — | Closed | 14 May 2024 |
| 154 | qwen3-4b-instruct-2507 | — | 45.8 | — | — | — | — | 6 Aug 2025 |
| 155 | DeepSeek-R1-Distill-Qwen-14BDeepSeek | 135.4 | 44.7 | — | — | — | Open | 20 Jan 2025 |
| 156 | Llama 3.1-70BMeta | 125.9 | 44.2 | — | — | — | Open | 23 Jul 2024 |
| 157 | WizardLM-2 8x22BMicrosoft | — | 43.4 | — | 66K | $0.62 | Open | 16 Apr 2024 |
| 158 | GPT-4 Turbo Preview (Nov 2023)OpenAI | — | 42.4 | — | — | — | Closed | 6 Nov 2023 |
| 159 | GPT-4 Turbo Preview (January 2024)OpenAI | — | 42.3 | — | — | — | Closed | 25 Jan 2024 |
| 160 | Qwen-TurboAlibaba (Qwen) | — | 41.8 | — | — | — | Closed | 1 Nov 2024 |
| 161 | Llama 3.2 90BMeta | 125.5 | 41.0 | — | — | — | Open | 24 Sep 2024 |
| 162 | Qwen2-72BAlibaba (Qwen) | 125.3 | 40.8 | — | — | — | Open | 7 Jun 2024 |
| 163 | Claude 3 SonnetAnthropic | 120.7 | 40.6 | — | — | — | Closed | 29 Feb 2024 |
| 164 | Llama 3-70BMeta | 122.9 | 40.6 | — | — | — | Open | 18 Apr 2024 |
| 165 | Gemini 1.5 Flash (May 2024)Google | 122.6 | 40.4 | — | — | — | Closed | 23 May 2024 |
| 166 | Gemma 3 12BGoogle | 123.5 | 39.5 | — | 131K | $0.075 | Open | 12 Mar 2025 |
| 167 | Mistral LargeMistral AI | 122.0 | 38.8 | — | 128K | $3.00 | Closed | 26 Feb 2024 |
| 168 | Claude 3.5 Haiku (Oct 2024)Anthropic | — | 38.1 | — | — | — | Closed | 22 Oct 2024 |
| 169 | Qwen3-1.7BAlibaba (Qwen) | — | 38.0 | — | — | — | Open | 29 Apr 2025 |
| 170 | GPT-4o-miniOpenAI | 126.6 | 37.7 | — | 128K | $0.26 | Closed | 18 Jul 2024 |
| 171 | Hermes 2 Theta Llama-3 70BNous Research | — | 37.5 | — | — | — | Open | 20 Jun 2024 |
| 172 | Gemma 2 27BGoogle | 122.1 | 36.5 | — | 8K | $0.65 | Open | 24 Jun 2024 |
| 173 | Claude 3 HaikuAnthropic | 118.3 | 36.3 | — | — | — | Closed | 7 Mar 2024 |
| 174 | GPT-4 (Mar 2023)OpenAI | 125.9 | 35.7 | — | — | — | Closed | 14 Mar 2023 |
| 175 | Qwen2.5-7BAlibaba (Qwen) | 118.4 | 35.5 | — | — | — | Open | 19 Sep 2024 |
| 176 | Claude 2Anthropic | 120.1 | 34.7 | — | — | — | Closed | 11 Jul 2023 |
| 177 | Mixtral 8x22BMistral AI | 122.0 | 34.1 | — | — | — | Open | 17 Apr 2024 |
| 178 | Gemini 1.0 ProGoogle | 117.0 | 34.0 | — | — | — | Closed | 13 Dec 2023 |
| 179 | Eurus-2-7B-PRIMETsinghua University,University of Illinois Urbana-Champaign (UIUC),Shanghai AI Lab,Peking University,Shanghai Jiao Tong University,CUHK Shenzhen Research Institute | — | 33.9 | — | — | — | Open | 31 Dec 2024 |
| 180 | DeepSeek-R1-Distill-Qwen-1.5BDeepSeek | — | 33.6 | — | — | — | Open | 20 Jan 2025 |
| 181 | Claude 2.1Anthropic | 119.2 | 33.0 | — | — | — | Closed | 21 Nov 2023 |
| 182 | Gemini 1.5 Flash 8BGoogle | — | 33.0 | — | — | — | Closed | 3 Oct 2024 |
| 183 | DBRXDatabricks | — | 32.9 | — | — | — | Open | 27 Mar 2024 |
| 184 | Yi-1.5-34B01.AI | — | 32.0 | — | — | — | Open | 13 May 2024 |
| 185 | Qwen1.5-32BAlibaba (Qwen) | — | 30.7 | — | — | — | Open | 3 Apr 2024 |
| 186 | GPT-4 (Jun 2023)OpenAI | 123.1 | 30.7 | — | — | — | Closed | 13 Jun 2023 |
| 187 | Mixtral 8x7BMistral AI | 118.4 | 30.6 | — | — | — | Open | 11 Dec 2023 |
| 188 | Mistral NemoMistral AI | 118.6 | 29.9 | — | 131K | $0.022 | Open | 18 Jul 2024 |
| 189 | Qwen1.5-72BAlibaba (Qwen) | — | 28.8 | — | — | — | Open | 4 Feb 2024 |
| 190 | Granite 4.0 MicroIBM | — | 28.3 | — | 131K | $0.041 | Open | 20 Oct 2025 |
| 191 | GPT-3.5 Turbo (Nov 2023)OpenAI | 118.5 | 28.0 | — | — | — | Closed | 6 Nov 2023 |
| 192 | phi-3-medium 14BMicrosoft | 121.2 | 27.6 | — | — | — | Open | 23 Apr 2024 |
| 193 | Gemma 2 9BGoogle | 119.8 | 27.5 | — | — | — | Open | 24 Jun 2024 |
| 194 | GPT-3.5 Turbo (Jan 2024)OpenAI | 115.6 | 27.2 | — | — | — | Closed | 25 Jan 2024 |
| 195 | Ministral 8BMistral AI | — | 27.1 | — | — | — | Open | 16 Oct 2024 |
| 196 | Llama 3.1-8BMeta | 116.5 | 27.0 | — | — | — | Open | 23 Jul 2024 |
| 197 | Llama 2-70BMeta | 113.6 | 26.3 | — | — | — | Open | 18 Jul 2023 |
| 198 | Llama 3-8BMeta | 116.3 | 26.1 | — | — | — | Open | 18 Apr 2024 |
| 199 | Ministral 3BMistral AI | 118.1 | 25.3 | — | — | — | Closed | 16 Oct 2024 |
| 200 | DeepSeek LLM 67BDeepSeek | 110.5 | 24.6 | — | — | — | Open | 29 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