Evaluation Suite
Benchmarks
Independent evaluation scores across knowledge, reasoning, math, coding and multimodal tasks — leaders in each column are highlighted.
Independent evaluation scores across knowledge, reasoning, math, coding and multimodal tasks — leaders in each column are highlighted.
| # | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Gemini 3.1 ProGoogle | 94.30% (column leader) | 80.60% | — | — | 44.70% | — | 51.40% | 54.20% | 80.50% | — | — | — | — | — | 77.10% (column leader) | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 2 | Claude Opus 4.7Anthropic | 94.20% | 87.60% | — | — | — | — | 54.70% | 64.30% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 3 | Claude Opus 4.8Anthropic | 93.60% | 88.60% (column leader) | — | — | 45.70% (column leader) | — | 57.90% (column leader) | 69.20% (column leader) | — | — | — | — | — | — | — | — | — | 74.60% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 4 | GPT-5.5OpenAI | 93.60% | — | — | — | 44.30% | — | 52.20% | 58.60% | — | — | — | — | — | — | — | — | — | 78.20% (column leader) | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 5 | GPT-5.4OpenAI | 92.80% | — | — | — | — | — | 39.80% | 57.70% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 6 | Gemini 3.5 FlashGoogle | 92.20% | — | — | — | 40.20% | — | — | 55.10% | 83.60% (column leader) | — | — | — | — | — | 72.10% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 7 | Gemini 3.5 ProGoogle | 91.80% | 78.40% | 89.70% (column leader) | 94.50% | 32.60% | 81.30% | — | — | 82.10% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 8 | GLM-5.2Z.ai (Zhipu AI) | 91.20% | — | — | — | — | — | — | 62.10% | — | — | 91% (column leader) | — | — | 99.20% (column leader) | — | — | — | — | — | — | — | — | — | — | — | — | 76.80% (column leader) | — | — | — | 48.90% (column leader) | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 20.90% (column leader) | — | — | 46.20% (column leader) | 74.40% (column leader) | — | — | 40.50% (column leader) | 54.70% (column leader) | — | — | — | — | — | — | 92.50% (column leader) | 94.40% (column leader) | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 63.70% (column leader) | — | — | — | — | — | — | — | — | — | 81% (column leader) | — | — | — | — | — | — |
| 9 | Kimi K2.6Moonshot AI | 90.50% | 80.20% | — | — | — | — | — | 58.60% | 79.40% | 83.20% | — | 76.70% (column leader) | — | 96.40% | — | — | 89.60% (column leader) | — | — | — | — | 54% (column leader) | — | — | — | — | — | — | — | — | — | — | 66.70% (column leader) | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 92.70% (column leader) | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 10 | Gemini 3 FlashGoogle | 90.40% | 78% | — | — | 33.70% | — | 43.50% | — | 81.20% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 11 | DeepSeek-V4-ProDeepSeek | 90.10% | 80.60% | 87.50% | — | — | 93.50% (column leader) | — | 55.40% | — | 83.40% (column leader) | 89.80% | 76.20% | 67.90% (column leader) | — | — | 37.70% (column leader) | — | — | — | 3,206 rating (column leader) | — | — | 95.20% (column leader) | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 90.20% (column leader) | — | — | — | — | — | — | — | 84.40% (column leader) | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 57.90% (column leader) | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 12 | Grok 4.3xAI | 90.10% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 13 | Claude Sonnet 4.6Anthropic | 89.90% | 79.60% | — | — | — | — | 49% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 14 | GPT-5 ProOpenAI | 89.60% | 78.40% | 88.20% | 96.50% (column leader) | — | 81.30% | 42.10% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 15 | Gemini 3 ProGoogle | 88.90% | 74.20% | 87.30% | 91.20% | 28.40% | 76.80% | — | — | 78.60% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 16 | DeepSeek-V4-FlashDeepSeek | 88.10% | 79% | 86.40% | — | — | 91.60% | — | — | — | 73.20% | 88.40% | 73.30% | 56.90% | — | — | 34.80% | — | — | — | 3,052 rating | — | — | 94.80% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 78.70% (column leader) | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 17 | GPT-5.4 miniOpenAI | 88% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 18 | Kimi K2.5Moonshot AI | 87.60% | 76.80% | 87.10% | 96.10% | — | — | — | — | 78.50% | 60.60% | — | — | 50.80% | — | — | — | — | — | — | — | — | 50.20% | — | — | — | — | — | — | — | — | — | 50.70% | — | — | 70% (column leader) | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 77.10% (column leader) | — | — | — | — | — | — | — | 30.10% (column leader) | 95.40% (column leader) | — | — | — | — | — | — | — | — | 81.80% (column leader) | — | — | — | 85% (column leader) | — | — | 61% (column leader) | — | — | 84.20% (column leader) | 90.10% (column leader) | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 92.30 points (column leader) | — | 57.40% (column leader) | — | — | — | 48.70% (column leader) | — | — | — | 73% (column leader) | — | — | — | — | — | — | 87.40% (column leader) | 86.60% (column leader) | — | — | — |
| 19 | Gemini 2.5 ProGoogle | 86.40% | 59.60% | — | 88% | 21.60% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 20 | GLM-5.1Z.ai (Zhipu AI) | 86.20% | — | — | — | — | — | — | — | — | 68% | 83.80% | — | — | 95.30% | — | — | — | — | — | — | — | — | — | 94% (column leader) | — | — | 71.80% | — | — | — | 42.70% | 58.40% (column leader) | 63.50% | — | — | — | — | — | — | — | — | — | — | 79.30% (column leader) | — | — | — | — | — | 68.70% (column leader) | — | — | — | — | 31% (column leader) | — | — | 52.30% (column leader) | — | — | — | — | 82.60% (column leader) | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 40.70% (column leader) | — | — | — | — | — |
| 21 | Grok 4.2xAI | 86% | 73% | 87% | 93% | 24% | — | 40% | — | — | — | — | — | — | — | 15.50% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 22 | GLM-4.7Z.ai (Zhipu AI) | 85.70% | 73.80% | 84.30% | 95.70% | — | — | — | — | — | 52% | 82% | 66.70% | 41% | — | — | 24.80% | 84.90% | — | — | — | — | — | — | 93.50% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 66.60% (column leader) | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 97.10% (column leader) | — | — | — | — | — | 42.80% (column leader) | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 87.40% (column leader) | — | — | 33.30% (column leader) | — | — | — | — | — | — | — |
| 23 | Claude Opus 4.6Anthropic | 85.40% | 79.80% | 87.90% | 90.50% | 18.60% | — | — | — | — | — | — | — | — | — | — | — | — | 51.20% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 24 | Claude Opus 4.5Anthropic | 83.10% | 76.40% | 86.20% | 87% | 15.90% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 25 | Grok 4.1xAI | 83% | 70% | 85.50% | 90% | 22% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 26 | Gemini 2.5 FlashGoogle | 82.80% | 60.40% | — | 72% | 11% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 27 | 82.50% | 68% | 84.50% | 88% | 19.50% | 72% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| 28 | GPT-5.5 miniOpenAI | 82.40% | 72.60% | 84.50% | 91% | — | 74.80% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 29 | Claude Opus 4.1Anthropic | 80.90% | 74.50% | 83.50% | 78% | 11.20% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 30 | Claude Sonnet 4.5Anthropic | 80.60% | 73.10% | 84% | 84.20% | 12.80% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 31 | Grok 4xAI | 80% | 65% | 83% | 86% | 19% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 32 | GPT-5.3OpenAI | 79.10% | 68.90% | 82.70% | 88.40% | — | 70.20% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 33 | Claude Sonnet 4.4Anthropic | 77.90% | 69.50% | 81.70% | 79.60% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 34 | Grok 4.20xAI | 77.60% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 35 | Qwen3-235B-A22B-Instruct-2507Qwen (Alibaba) | 77.50 accuracy % | — | 83 accuracy % | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 88.70 accuracy % | — | — | — | — | — | — | — | — | — | — | — | 57.30 accuracy % (column leader) | 70.30 accuracy % (column leader) | — | 41.80 accuracy % (column leader) | 79.20 win rate % (column leader) | — | 70.90 accuracy % (column leader) | — | — | — | — | 87.50 score (column leader) | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 55.40 accuracy % (column leader) | — | — | — | — | — | 75.40 accuracy % (column leader) | — | 51.80 accuracy % (column leader) | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 79.40 accuracy % (column leader) | 93.10 accuracy % (column leader) | — | 77.50 accuracy % (column leader) | 87.90 accuracy % (column leader) | — | — | — | 50.20 accuracy % (column leader) | — | — | — | 54.30 accuracy % (column leader) | — | 62.60 accuracy % (column leader) | — | — | — | 74.60 accuracy % (column leader) | — | — | — | — | — | 85.20 score (column leader) | 95 accuracy % (column leader) | — |
| 36 | GPT-5.2OpenAI | 76.30% | 65.10% | 80.90% | 85% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 37 | Kimi K2 (Instruct)Moonshot AI | 75.10 % avg@8 | 65.80 % pass@1 (single attempt, agentic) | — | 49.50 % avg@64 | — | — | — | — | — | — | — | 47.30 % pass@1 (single attempt, agentic) | — | — | — | — | 53.70 % pass@1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 76.50 % accuracy (column leader) | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 27.10 % pass@1 (column leader) | — | — | — | — | — | — | — | — | — | — | 66.10 score (column leader) | — | — | — | — | — | — | — | — | — |
| 38 | Grok 4 FastxAI | 75% | 58% | 79.50% | 78% | — | 63% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 39 | GPT-5.1OpenAI | 73.50% | 61.70% | 79.10% | 82.60% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 40 | GPT-5.2 miniOpenAI | 71.80% | 58.40% | 77.50% | 80.20% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 41 | GPT-5OpenAI | 70.20% | 56.80% | 76.40% | 78.50% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 42 | Llama 4 MaverickMeta | 69.80 accuracy (0-shot) | — | 80.50 macro_avg/acc (0-shot) | — | — | 43.40 pass@1 (0-shot, 10/01/2024-02/01/2025) | — | — | — | — | — | — | — | — | — | — | — | — | 90 relaxed_accuracy (0-shot) (column leader) | — | 94.40 anls (0-shot) (column leader) | — | — | — | — | 73.70 accuracy (0-shot) (column leader) | — | 92.30 average/em (0-shot) (column leader) | 73.40 accuracy (0-shot) (column leader) | 59.60 accuracy (0-shot, avg of Standard and Vision) (column leader) | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 1,417 ELO (column leader) | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 43 | GPT-5.5 nanoOpenAI | 68.90% | 54.20% | 74.10% | 76.80% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 44 | Claude Haiku 4.4Anthropic | 68.40% | 58.20% | 75.30% | 66.10% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 45 | Grok 3xAI | 68% | — | 79% | 52% | — | 55% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 46 | Gemini 2.5 Flash-LiteGoogle | 64.50% | 41.30% | 76.20% | 68.90% | — | 52.40% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 47 | Gemini 2.0 ProGoogle | 62.10% | 45.80% | 78.90% | 58.30% | — | 49.60% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 48 | Llama 4 ScoutMeta | 57.20 accuracy (0-shot) | — | 74.30 macro_avg/acc (0-shot) | — | — | 32.80 pass@1 (0-shot, 10/01/2024-02/01/2025) | — | — | — | — | — | — | — | — | — | — | — | — | 88.80 relaxed_accuracy (0-shot) | — | 94.40 anls (0-shot) (column leader) | — | — | — | — | 70.70 accuracy (0-shot) | — | 90.60 average/em (0-shot) | 69.40 accuracy (0-shot) | 52.20 accuracy (0-shot) | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 50.30 em_maj1@1 (4-shot) (column leader) | — | — | — | — | — | — | — | — | 79.60 macro_avg/acc_char (5-shot) (column leader) | — | 58.20 macro_avg/em (5-shot) (column leader) | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 49 | Gemini 2.0 FlashGoogle | 54.70% | 34.20% | 71.60% | 49.10% | — | 40.80% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 50 | Gemini 1.5 ProGoogle | 46.20% | 22.50% | 68.40% | 31.70% | — | 34.90% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 51 | Mistral Small 4Mistral AI | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 0.72 score (column leader) | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 52 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 92.10 accuracy (column leader) | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 77.30 overall_ast_summary/macro_avg/valid (column leader) | — | — | — | — | — | — | — | — | — | — | — | 50.50 accuracy (column leader) | — | — | — | — | — | — | — | — | — | — | — | — | 88.40 pass@1 (column leader) | — | — | — | — | — | — | — | — | — | 77 sympy_intersection_score (column leader) | — | — | — | 87.60 pass@1 (column leader) | — | — | 91.10 exact_match (column leader) | — | 86 macro_avg/acc (column leader) | — | 68.90 macro_avg/acc (column leader) | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| 53 | GLM-4.6Z.ai (Zhipu AI) | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 48.60 % win rate (column leader) | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 54 | GPT-5.5 ProOpenAI | — | — | — | — | — | — | 57.20% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 55 | Kimi K2.7 CodeMoonshot AI | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 46.90 score (column leader) | 62 score (column leader) | — | — | — | — | — | — | — | — | — | — | 76 score (column leader) | 81.10 score (column leader) | — | 35.10 score (column leader) | — | — | — | — | — | — | — | — | — | — | — | — | — | 53.60 score (column leader) | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 56 | Mistral Medium 3.5Mistral AI | — | 77.60 % resolved | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 91.40% (column leader) |
| 57 | Claude Haiku 4.5Anthropic | — | 73.30% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
| 58 | — | 70.80% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — |
Every score is sourced from a primary publication (provider report or independent eval) and carries a verification date — click a model for its full sourced spec. Leaders in each column are highlighted; a “—” means no verified result for that suite yet.