Simplify
LiveBench · 28 models
| Rank | Model | Score |
|---|---|---|
| 1 | gpt-5.5-high | 71.35 |
| 2 | gemini-3.1-pro-preview-high | 71.05 |
| 3 | claude-opus-4-8-xhigh-effort | 70.517 |
| 4 | gpt-5.4-xhigh | 70 |
| 5 | gemini-3.5-flash-high | 69.1 |
| 6 | gpt-5.5-xhigh | 66.317 |
| 7 | claude-opus-4-7-xhigh-effort | 65.5 |
| 8 | qwen3.7-max | 64.083 |
| 9 | claude-fable-5-xhigh-effort | 63.233 |
| 10 | claude-sonnet-4-6-thinking-auto-medium-effort | 62.933 |
| 11 | gpt-5.4-nano-xhigh | 62.75 |
| 12 | grok-build-0.1 | 62.6 |
| 13 | kimi-k2.6-thinking | 61.417 |
| 14 | claude-sonnet-5-xhigh-effort | 60.65 |
| 15 | gpt-5.2-codex | 60.567 |
| 16 | claude-opus-4-6-thinking-auto-high-effort | 59.15 |
| 17 | gpt-5.5 | 58.733 |
| 18 | grok-4.3 | 57.6 |
| 19 | minimax-m3 | 56.617 |
| 20 | deepseek-v4-pro | 55.933 |
| 21 | glm-5.2 | 55.667 |
| 22 | claude-opus-4-5-20251101-thinking-64k-high-effort | 54.95 |
| 23 | gpt-5.2-2025-12-11-high | 54.083 |
| 24 | gpt-5.4-mini-xhigh | 54.067 |
| 25 | deepseek-v4-flash | 54.05 |
| 26 | qwen3.6-plus | 51.567 |
| 27 | qwen3.6-27b | 50.733 |
| 28 | kimi-k2.7-code | 49.75 |