Summarize
LiveBench · 28 models
| Rank | Model | Score |
|---|---|---|
| 1 | gemini-3.1-pro-preview-high | 88.233 |
| 2 | qwen3.7-max | 83.8 |
| 3 | gemini-3.5-flash-high | 82.583 |
| 4 | claude-fable-5-xhigh-effort | 78.517 |
| 5 | claude-opus-4-8-xhigh-effort | 74.55 |
| 6 | gpt-5.5 | 73.417 |
| 7 | gpt-5.5-high | 73.1 |
| 8 | gpt-5.5-xhigh | 72.317 |
| 9 | gpt-5.4-nano-xhigh | 71.767 |
| 10 | claude-sonnet-5-xhigh-effort | 71.217 |
| 11 | deepseek-v4-pro | 69.5 |
| 12 | deepseek-v4-flash | 68.85 |
| 13 | gpt-5.4-xhigh | 68.417 |
| 14 | glm-5.2 | 68.367 |
| 15 | kimi-k2.6-thinking | 67.5 |
| 16 | grok-build-0.1 | 67.367 |
| 17 | claude-opus-4-7-xhigh-effort | 66.283 |
| 18 | claude-opus-4-6-thinking-auto-high-effort | 65.15 |
| 19 | qwen3.6-plus | 64.317 |
| 20 | claude-opus-4-5-20251101-thinking-64k-high-effort | 63.717 |
| 21 | gpt-5.2-codex | 63.383 |
| 22 | gpt-5.2-2025-12-11-high | 63.2 |
| 23 | claude-sonnet-4-6-thinking-auto-medium-effort | 61.65 |
| 24 | gpt-5.4-mini-xhigh | 59.633 |
| 25 | grok-4.3 | 58.417 |
| 26 | kimi-k2.7-code | 58.317 |
| 27 | minimax-m3 | 53.933 |
| 28 | qwen3.6-27b | 52.617 |