Language
LiveBench · 28 models
| Rank | Model | Score |
|---|---|---|
| 1 | claude-fable-5-xhigh-effort | 89.4577 |
| 2 | gpt-5.5-high | 87.76 |
| 3 | gpt-5.5-xhigh | 87.363 |
| 4 | gpt-5.5 | 85.5703 |
| 5 | gemini-3.1-pro-preview-high | 85.376 |
| 6 | gemini-3.5-flash-high | 84.5843 |
| 7 | claude-opus-4-6-thinking-auto-high-effort | 83.2697 |
| 8 | gpt-5.4-xhigh | 82.6337 |
| 9 | claude-opus-4-8-xhigh-effort | 81.4173 |
| 10 | claude-opus-4-5-20251101-thinking-64k-high-effort | 81.261 |
| 11 | gpt-5.2-2025-12-11-high | 79.809 |
| 12 | qwen3.7-max | 79.739 |
| 13 | deepseek-v4-pro | 78.1303 |
| 14 | claude-opus-4-7-xhigh-effort | 77.914 |
| 15 | kimi-k2.7-code | 77.9057 |
| 16 | minimax-m3 | 76.8357 |
| 17 | glm-5.2 | 76.2417 |
| 18 | claude-sonnet-4-6-thinking-auto-medium-effort | 76.1027 |
| 19 | kimi-k2.6-thinking | 75.1413 |
| 20 | qwen3.6-plus | 74.9893 |
| 21 | claude-sonnet-5-xhigh-effort | 74.9703 |
| 22 | gpt-5.2-codex | 73.6783 |
| 23 | grok-4.3 | 73.58 |
| 24 | grok-build-0.1 | 72.46 |
| 25 | gpt-5.4-mini-xhigh | 70.9517 |
| 26 | deepseek-v4-flash | 70.124 |
| 27 | qwen3.6-27b | 63.3043 |
| 28 | gpt-5.4-nano-xhigh | 62.507 |