Reasoning
LiveBench · 28 models
| Rank | Model | Score |
|---|---|---|
| 1 | claude-opus-4-8-xhigh-effort | 89.7115 |
| 2 | gpt-5.5-high | 89.673 |
| 3 | gpt-5.5-xhigh | 89.6538 |
| 4 | claude-sonnet-5-xhigh-effort | 88.6923 |
| 5 | claude-opus-4-6-thinking-auto-high-effort | 88.673 |
| 6 | gpt-5.4-xhigh | 88.1155 |
| 7 | claude-fable-5-xhigh-effort | 87.7115 |
| 8 | gpt-5.5 | 87.274 |
| 9 | claude-opus-4-7-xhigh-effort | 87.1923 |
| 10 | claude-sonnet-4-6-thinking-auto-medium-effort | 84.7693 |
| 11 | gemini-3.1-pro-preview-high | 84.0048 |
| 12 | qwen3.7-max | 83.3365 |
| 13 | gpt-5.2-2025-12-11-high | 83.2115 |
| 14 | kimi-k2.7-code | 82.8078 |
| 15 | deepseek-v4-pro | 82.6923 |
| 16 | gemini-3.5-flash-high | 82.0048 |
| 17 | gpt-5.4-nano-xhigh | 81.097 |
| 18 | claude-opus-4-5-20251101-thinking-64k-high-effort | 80.0865 |
| 19 | kimi-k2.6-thinking | 79.375 |
| 20 | glm-5.2 | 78.625 |
| 21 | gpt-5.2-codex | 77.7115 |
| 22 | grok-build-0.1 | 76.3703 |
| 23 | qwen3.6-plus | 75.827 |
| 24 | minimax-m3 | 74.4808 |
| 25 | gpt-5.4-mini-xhigh | 71.3238 |
| 26 | grok-4.3 | 70.822 |
| 27 | deepseek-v4-flash | 70.5818 |
| 28 | qwen3.6-27b | 70.2838 |