Global Average
LiveBench · 28 models
| Rank | Model | Score |
|---|---|---|
| 1 | gpt-5.5-xhigh | 79.9142 |
| 2 | claude-fable-5-xhigh-effort | 79.5343 |
| 3 | claude-opus-4-8-xhigh-effort | 78.9275 |
| 4 | gpt-5.5-high | 78.7494 |
| 5 | gpt-5.4-xhigh | 77.9724 |
| 6 | gemini-3.1-pro-preview-high | 77.1322 |
| 7 | claude-opus-4-7-xhigh-effort | 76.5294 |
| 8 | claude-sonnet-5-xhigh-effort | 74.8492 |
| 9 | gemini-3.5-flash-high | 74.6378 |
| 10 | gpt-5.2-2025-12-11-high | 74.635 |
| 11 | claude-opus-4-6-thinking-auto-high-effort | 74.5199 |
| 12 | gpt-5.2-codex | 73.9753 |
| 13 | glm-5.2 | 73.179 |
| 14 | qwen3.7-max | 73.1366 |
| 15 | claude-sonnet-4-6-thinking-auto-medium-effort | 72.99 |
| 16 | claude-opus-4-5-20251101-thinking-64k-high-effort | 72.5822 |
| 17 | gpt-5.5 | 72.154 |
| 18 | deepseek-v4-pro | 71.5723 |
| 19 | kimi-k2.6-thinking | 70.5388 |
| 20 | gpt-5.4-nano-xhigh | 69.5764 |
| 21 | qwen3.6-plus | 68.9061 |
| 22 | kimi-k2.7-code | 68.4117 |
| 23 | grok-build-0.1 | 67.781 |
| 24 | minimax-m3 | 67.2568 |
| 25 | gpt-5.4-mini-xhigh | 66.374 |
| 26 | deepseek-v4-flash | 65.4811 |
| 27 | qwen3.6-27b | 64.0271 |
| 28 | grok-4.3 | 62.2474 |