Benchmarks · reasoning
LiveBench
A periodically refreshed suite of objectively graded tasks with separate category scores and an overall category mean. Maintained by LiveBench team. Score: Overall mean of category averages, with source-published exceptions retained.
56 models · 57 results · data as of 2026-10-29 · livebench.ai ↗
Leaderboard
Fable 5.1 max
All results
57 rows| # | Model | Effort | LiveBench |
|---|---|---|---|
| 1 | Fable 5.1 | max | 83.4% |
| 2 | Opus 5.5 | max | 83.2% |
| 3 | Fable 5 | max | 83.0% |
| 4 | GPT-6 Astra | max | 82.2% |
| 5 | Opus 5.5 | xhigh | 82.1% |
| 6 | Muse Spark 1.3 | xhigh | 81.6% |
| 7 | DeepSeek V4.1 Flash | max | 81.1% |
| 8 | GPT-5.6 Sol | max | 81.0% |
| 9 | GPT-5.5 | xhigh | 80.2% |
| 10 | Opus 5 | max | 80.1% |
| 11 | GPT-6 Sol | max | 79.3% |
| 12 | Kimi K3 | max | 79.2% |
| 13 | Gemini 3.7 Flash | high | 78.8% |
| 14 | Qwen 3.8 Max | max | 78.5% |
| 15 | Grok 4.6 | max | 78.0% |
| 16 | GPT-5.4 | xhigh | 78.0% |
| 17 | Muse Spark 1.2 | xhigh | 78.0% |
| 18 | GPT-5.6 Terra | max | 77.9% |
| 19 | DeepSeek V4 Pro 0813 | max | 77.4% |
| 20 | Grok 4.7 | xhigh | 77.4% |
| 21 | Gemini 3.1 Pro | high | 77.0% |
| 22 | Opus 4.7 | xhigh | 76.5% |
| 23 | Opus 4.8 | max | 76.2% |
| 24 | Qwen 3.8 Flash | max | 76.2% |
| 25 | GLM 5.3 | max | 76.1% |
| 26 | Sonnet 5 | xhigh | 76.0% |
| 27 | Gemini 3.8 Flash | high | 75.8% |
| 28 | Grok 4.5 | max | 75.8% |
| 29 | Muse Spark 1.1 | xhigh | 75.3% |
| 30 | Qwen 3.8 27B | max | 75.3% |