Consecutive Events
LiveBench · 28 models
| Rank | Model | Score |
|---|---|---|
| 1 | claude-sonnet-4-6-thinking-auto-medium-effort | 92.683 |
| 2 | claude-opus-4-7-xhigh-effort | 89.521 |
| 3 | claude-opus-4-8-xhigh-effort | 89.205 |
| 4 | gpt-5.2-codex | 89.016 |
| 5 | gpt-5.2-2025-12-11-high | 88.913 |
| 6 | gpt-5.5-xhigh | 88.823 |
| 7 | gpt-5.5-high | 87.637 |
| 8 | gpt-5.4-xhigh | 86.19 |
| 9 | gemini-3.1-pro-preview-high | 85.239 |
| 10 | minimax-m3 | 84.614 |
| 11 | claude-fable-5-xhigh-effort | 83.252 |
| 12 | claude-opus-4-5-20251101-thinking-64k-high-effort | 79.363 |
| 13 | glm-5.2 | 79.276 |
| 14 | gpt-5.5 | 78.23 |
| 15 | deepseek-v4-pro | 75.421 |
| 16 | claude-sonnet-5-xhigh-effort | 74.741 |
| 17 | qwen3.7-max | 71.8 |
| 18 | qwen3.6-27b | 70.395 |
| 19 | grok-build-0.1 | 69.728 |
| 20 | qwen3.6-plus | 67.042 |
| 21 | claude-opus-4-6-thinking-auto-high-effort | 63.467 |
| 22 | gpt-5.4-mini-xhigh | 62.972 |
| 23 | deepseek-v4-flash | 59.915 |
| 24 | gpt-5.4-nano-xhigh | 54.301 |
| 25 | kimi-k2.6-thinking | 51.268 |
| 26 | kimi-k2.7-code | 48.277 |
| 27 | gemini-3.5-flash-high | 47.994 |
| 28 | grok-4.3 | 28.029 |