| 1SOTA | deepseek-v4.1-flash-max | — | 98.2 | 98.2 |
| 2 | claude-fable-5-1-max-effort | — | 96.5 | 96.5 |
| 3 | smaug-agentic | — | 94.7 | 94.7 |
| 4 | claude-fable-5-max-effort | — | 93.0 | 93.0 |
| 5 | claude-opus-5-max-effort | — | 91.2 | 91.2 |
| 6 | muse-spark-1.3-xhigh | — | 89.5 | 89.5 |
| 7 | kimi-k3 | — | 87.7 | 87.7 |
| 8 | glm-5.3 | — | 86.0 | 86.0 |
| 9 | qwen3.8-max | — | 84.2 | 84.2 |
| 10 | claude-sonnet-5-xhigh-effort | — | 82.5 | 82.5 |
| 11 | smaug-flash | — | 80.7 | 80.7 |
| 12 | gpt-5.6-sol-max | — | 78.9 | 78.9 |
| 13 | qwen3.8-27b | — | 77.2 | 77.2 |
| 14 | smaug-mini | — | 75.4 | 75.4 |
| 15 | gpt-6-astra-max | — | 73.7 | 73.7 |
| 16 | gemini-3.7-flash-high | — | 71.9 | 71.9 |
| 17 | deepseek-v4-flash-vision-exp | — | 70.2 | 70.2 |
| 18 | qwen3.8-flash-next | — | 68.4 | 68.4 |
| 19 | muse-spark-1.1-xhigh | — | 66.7 | 66.7 |
| 20 | glm-5.3-flash | — | 64.9 | 64.9 |
| 21 | muse-spark-1.2-xhigh | — | 63.2 | 63.2 |
| 22 | gpt-5.5-xhigh | — | 61.4 | 61.4 |
| 23 | grok-4.6 | — | 59.6 | 59.6 |
| 24 | gpt-5.6-terra-max | — | 57.9 | 57.9 |
| 25 | deepseek-v4-pro-0813 | — | 56.1 | 56.1 |
| 26 | gpt-5.4-xhigh | — | 54.4 | 54.4 |
| 27 | claude-opus-4-7-xhigh-effort | — | 52.6 | 52.6 |
| 28 | gpt-5.2-codex | — | 50.9 | 50.9 |
| 29 | claude-opus-4-8-max-effort | — | 49.1 | 49.1 |
| 30 | glm-5.2 | — | 47.4 | 47.4 |
| 31 | gpt-5.6-luna-max | — | 45.6 | 45.6 |
| 32 | ox-alpha-max | — | 43.9 | 43.9 |
| 33 | gemini-3.8-flash-high | — | 42.1 | 42.1 |
| 34 | grok-4.5 | — | 40.4 | 40.4 |
| 35 | claude-opus-4-6-thinking-auto-high-effort | — | 38.6 | 38.6 |
| 36 | gemini-3.5-flash-high | — | 36.8 | 36.8 |
| 37 | gpt-5.2-2025-12-11-high | — | 35.1 | 35.1 |
| 38 | kimi-k2.6-thinking | — | 33.3 | 33.3 |
| 39 | deepseek-v4-flash-0731 | — | 31.6 | 31.6 |
| 40 | inkling-xhigh | — | 29.8 | 29.8 |
| 41 | gemini-3.5-flash-lite-high | — | 28.1 | 28.1 |
| 42 | claude-sonnet-4-6-thinking-auto-medium-effort | — | 26.3 | 26.3 |
| 43 | gemini-3.6-flash-high | — | 24.6 | 24.6 |
| 44 | gemini-3.1-pro-preview-high | — | 22.8 | 22.8 |
| 45 | kimi-k2.7-code | — | 21.1 | 21.1 |
| 46 | gpt-5.4-nano-xhigh | — | 19.3 | 19.3 |
| 47 | qwen3.6-plus | — | 17.5 | 17.5 |
| 48 | qwen3.7-max | — | 15.8 | 15.8 |
| 49 | claude-opus-4-5-20251101-thinking-64k-high-effort | — | 14.0 | 14.0 |
| 50 | gpt-5.4-mini-xhigh | — | 12.3 | 12.3 |