Math Comp
LiveBench · 28 models
| Rank | Model | Score |
|---|---|---|
| 1 | claude-opus-4-7-xhigh-effort | 98.039 |
| 2 | claude-opus-4-8-xhigh-effort | 97.059 |
| 2 | deepseek-v4-flash | 97.059 |
| 2 | qwen3.7-max | 97.059 |
| 5 | deepseek-v4-pro | 96.078 |
| 5 | gemini-3.1-pro-preview-high | 96.078 |
| 5 | glm-5.2 | 96.078 |
| 5 | gpt-5.5 | 96.078 |
| 5 | gpt-5.5-high | 96.078 |
| 5 | gpt-5.5-xhigh | 96.078 |
| 5 | kimi-k2.6-thinking | 96.078 |
| 12 | claude-fable-5-xhigh-effort | 95.098 |
| 12 | claude-opus-4-5-20251101-thinking-64k-high-effort | 95.098 |
| 12 | claude-opus-4-6-thinking-auto-high-effort | 95.098 |
| 12 | claude-sonnet-5-xhigh-effort | 95.098 |
| 12 | gemini-3.5-flash-high | 95.098 |
| 12 | gpt-5.2-2025-12-11-high | 95.098 |
| 12 | gpt-5.2-codex | 95.098 |
| 12 | gpt-5.4-nano-xhigh | 95.098 |
| 12 | grok-4.3 | 95.098 |
| 12 | grok-build-0.1 | 95.098 |
| 22 | claude-sonnet-4-6-thinking-auto-medium-effort | 94.118 |
| 22 | gpt-5.4-mini-xhigh | 94.118 |
| 22 | gpt-5.4-xhigh | 94.118 |
| 22 | kimi-k2.7-code | 94.118 |
| 26 | qwen3.6-plus | 93.137 |
| 27 | qwen3.6-27b | 92.157 |
| 28 | minimax-m3 | 91.176 |