Data Analysis
LiveBench · 28 models
| Rank | Model | Score |
|---|---|---|
| 1 | gpt-5.5-xhigh | 81.5757 |
| 2 | gpt-5.5-high | 80.443 |
| 3 | gpt-5.4-xhigh | 79.3133 |
| 4 | claude-fable-5-xhigh-effort | 78.693 |
| 5 | gemini-3.1-pro-preview-high | 78.5413 |
| 6 | claude-opus-4-8-xhigh-effort | 78.344 |
| 7 | claude-opus-4-7-xhigh-effort | 78.2637 |
| 8 | gpt-5.2-codex | 78.204 |
| 9 | gpt-5.2-2025-12-11-high | 78.1633 |
| 10 | claude-sonnet-4-6-thinking-auto-medium-effort | 77.946 |
| 11 | gpt-5.5 | 76.987 |
| 12 | minimax-m3 | 76.1663 |
| 13 | deepseek-v4-pro | 74.5377 |
| 14 | claude-opus-4-5-20251101-thinking-64k-high-effort | 74.4417 |
| 15 | glm-5.2 | 73.7397 |
| 16 | qwen3.7-max | 71.786 |
| 17 | claude-sonnet-5-xhigh-effort | 71.7407 |
| 18 | grok-build-0.1 | 70.794 |
| 19 | gpt-5.4-mini-xhigh | 70.7857 |
| 20 | qwen3.6-27b | 70.4267 |
| 21 | qwen3.6-plus | 69.9117 |
| 22 | claude-opus-4-6-thinking-auto-high-effort | 69.893 |
| 23 | deepseek-v4-flash | 68.023 |
| 24 | gpt-5.4-nano-xhigh | 67.6427 |
| 25 | kimi-k2.6-thinking | 65.1343 |
| 26 | gemini-3.5-flash-high | 64.8573 |
| 27 | kimi-k2.7-code | 62.6573 |
| 28 | grok-4.3 | 55.7727 |