Table Join
LiveBench · 28 models
| Rank | Model | Score |
|---|---|---|
| 1 | gpt-5.5-xhigh | 55.904 |
| 2 | claude-fable-5-xhigh-effort | 54.788 |
| 3 | gpt-5.5-high | 53.692 |
| 4 | gpt-5.5 | 52.731 |
| 5 | gemini-3.1-pro-preview-high | 52.346 |
| 6 | gpt-5.4-xhigh | 51.75 |
| 7 | gpt-5.4-nano-xhigh | 50.588 |
| 8 | gemini-3.5-flash-high | 50.5 |
| 9 | gpt-5.4-mini-xhigh | 49.385 |
| 10 | deepseek-v4-pro | 48.192 |
| 11 | claude-opus-4-6-thinking-auto-high-effort | 48.173 |
| 12 | claude-opus-4-8-xhigh-effort | 47.788 |
| 13 | kimi-k2.7-code | 47.538 |
| 14 | claude-opus-4-7-xhigh-effort | 47.231 |
| 15 | deepseek-v4-flash | 46.115 |
| 16 | kimi-k2.6-thinking | 46.096 |
| 17 | claude-opus-4-5-20251101-thinking-64k-high-effort | 45.923 |
| 18 | glm-5.2 | 45.865 |
| 19 | minimax-m3 | 45.846 |
| 20 | gpt-5.2-codex | 45.596 |
| 21 | gpt-5.2-2025-12-11-high | 45.577 |
| 22 | qwen3.7-max | 45.519 |
| 23 | claude-sonnet-4-6-thinking-auto-medium-effort | 45.077 |
| 24 | qwen3.6-plus | 44.654 |
| 25 | qwen3.6-27b | 42.846 |
| 26 | grok-build-0.1 | 42.654 |
| 27 | claude-sonnet-5-xhigh-effort | 42.442 |
| 28 | grok-4.3 | 41.25 |