Evaluation sources/LiveBench Coding
ObservingCoding
LiveBench Coding
LiveBench · Public model evaluation results from LiveBench Coding.
Model results from this source
| Claude Opus 5.5 | 78.7314 | 78.7 | 2026-06-25 |
| DeepSeek V4.1 Flash | 78.3784 | 78.4 | 2026-06-25 |
| Claude Fable 5.1 | 74.1864 | 74.2 | 2026-06-25 |
| Claude Fable 5 | 71.6998 | 71.7 | 2026-06-25 |
| Claude Opus 5 | 71.6994 | 71.7 | 2026-06-25 |
| Muse Spark 1.3 | 70.8796 | 70.9 | 2026-06-25 |
| Claude Sonnet 5.5 | 70.3344 | 70.3 | 2026-06-25 |
| Muse Wonder | 69.9084 | 69.9 | 2026-06-25 |
| Kimi K3 | 69.8812 | 69.9 | 2026-06-25 |
| GLM 5.3 | 68.1254 | 68.1 | 2026-06-25 |
| Qwen3.8 Max | 67.9368 | 67.9 | 2026-06-25 |
| Claude Sonnet 5 | 67.9084 | 67.9 | 2026-06-25 |
| GPT-5.6 Sol | 67.3036 | 67.3 | 2026-06-25 |
| GPT-6 Astra | 66.5372 | 66.5 | 2026-06-25 |
| GPT-6.1 Sol | 66.357 | 66.4 | 2026-06-25 |
| Muse Spark 1.1 | 65.9846 | 66.0 | 2026-06-25 |
| GLM-5.3 Flash | 65.6406 | 65.6 | 2026-06-25 |
| Muse Spark 1.2 | 65.562 | 65.6 | 2026-06-25 |
| Claude Haiku 5.5 | 65.4482 | 65.4 | 2026-06-25 |
| GPT-5.5 | 65.2536 | 65.3 | 2026-06-25 |
| Mistral Large 4 | 65.1664 | 65.2 | 2026-06-25 |
| Grok 4.6 | 64.9224 | 64.9 | 2026-06-25 |
| GPT-6 Sol | 64.434 | 64.4 | 2026-06-25 |
| GPT-5.6 Terra | 64.268 | 64.3 | 2026-06-25 |
| DeepSeek V4 Pro 0813 | 63.8332 | 63.8 | 2026-06-25 |
| GPT-5.4 | 63.3196 | 63.3 | 2026-06-25 |
| Grok 4.7 | 63.2572 | 63.3 | 2026-06-25 |
| Claude Opus 4.7 | 63.229 | 63.2 | 2026-06-25 |
| Claude Opus 4.8 | 63.0342 | 63.0 | 2026-06-25 |
| GLM-5.2 | 62.9222 | 62.9 | 2026-06-25 |
| GPT-6 Luna | 62.3072 | 62.3 | 2026-06-25 |
| GPT-5.6 Luna | 62.2266 | 62.2 | 2026-06-25 |
| Gemini 3.8 Flash | 61.541 | 61.5 | 2026-06-25 |
| Grok 4.5 | 61.313 | 61.3 | 2026-06-25 |
| Claude Opus 4.6 | 60.6676 | 60.7 | 2026-06-25 |
| GPT-5.2 | 60.5802 | 60.6 | 2026-06-25 |
| Kimi K2.6 | 59.5784 | 59.6 | 2026-06-25 |
| DeepSeek V4 Flash 0731 | 58.0544 | 58.1 | 2026-06-25 |
| Inkling | 58.0442 | 58.0 | 2026-06-25 |
| Gemini 3.5 Flash Lite | 57.5802 | 57.6 | 2026-06-25 |
| Claude Sonnet 4.6 | 57.2842 | 57.3 | 2026-06-25 |
| Gemini 3.6 Flash | 57.2058 | 57.2 | 2026-06-25 |
| Gemini 3.1 Pro Preview | 57.0666 | 57.1 | 2026-06-25 |
| Kimi K2.7 Code | 56.9774 | 57.0 | 2026-06-25 |
| Qwen3.6 Plus | 56.092 | 56.1 | 2026-06-25 |
| Qwen3.7 Max | 55.8392 | 55.8 | 2026-06-25 |
| Claude Opus 4.5 | 55.6798 | 55.7 | 2026-06-25 |
| GPT-5.4 mini | 53.6496 | 53.6 | 2026-06-25 |
| Grok Build 0.1 | 53.639 | 53.6 | 2026-06-25 |
| DeepSeek V4 Pro | 53.5732 | 53.6 | 2026-06-25 |
| Qwen3.6 27B | 52.2896 | 52.3 | 2026-06-25 |
| MiniMax-M3 | 51.6748 | 51.7 | 2026-06-25 |
| Nemotron 3 Ultra 550B A55B | 51.5216 | 51.5 | 2026-06-25 |
| DeepSeek V4 Flash | 50.2668 | 50.3 | 2026-06-25 |
| Grok 4.3 | 39.0942 | 39.1 | 2026-06-25 |