LiveBench · Reasoning
The Frontier
Best score over time · one chart, every benchmark
Full rankings
40 models tested · sorted by score
| # | Model | Score |
|---|---|---|
| 1 | 84.6 | |
| 2 | 83.3 | |
| 3 | 82.8 | |
| 4 | 82.7 | |
| 5 | 82.0 | |
| 6 | 78.6 | |
| 7 | 77.7 | |
| 8 | 76.4 | |
| 9 | 75.8 | |
| 10 | 74.8 | |
| 11 | 74.5 | |
| 12 | 72.5 | |
| 13 | 70.8 | |
| 14 | 70.6 | |
| 15 | 70.3 | |
| 16 | 69.7 | |
| 17 | 69.1 | |
| 18 | 64.7 | |
| 19 | 63.5 | |
| 20 | 62.9 | |
| 21 | 62.1 | |
| 22 | 59.7 | |
| 23 | 59.4 | |
| 24 | 59.4 | |
| 25 | 59.3 | |
| 26 | 58.6 | |
| 27 | 58.4 | |
| 28 | 58.2 | |
| 29 | 56.1 | |
| 30 | 54.8 | |
| 31 | 45.5 | |
| 32 | 44.3 | |
| 33 | 39.2 | |
| 34 | 37.5 | |
| 35 | 37.2 | |
| 36 | 35.5 | |
| 37 | 34.4 | |
| 38 | 27.7 | |
| 39 | 21.9 | |
| 40 | 17.4 |
Score distribution
Where models cluster
Correlated benchmarks
Pearson r · original research
Benchmarks that track with LiveBench · Reasoning
Pearson correlation across models scored on both benchmarks. Closer to 1 = strongly predictive.
Frequently asked
About LiveBench · Reasoning
What does LiveBench · Reasoning measure?
LiveBench · Reasoning is a knowledge benchmark in the BenchGecko catalog. 40 AI models have been tested on it. Scores range from 17.4 to 84.6 out of 100.
Which model leads on LiveBench · Reasoning?
GPT-5.1-Codex-Max from OpenAI leads LiveBench · Reasoning with a score of 84.6. The median score across 40 tested models is 62.5.
Is LiveBench · Reasoning saturated?
No · the top score is 84.6 out of 100 (85%). There is still meaningful room for improvement on LiveBench · Reasoning.
Does LiveBench · Reasoning predict performance on other benchmarks?
Yes · LiveBench · Reasoning scores correlate 1.00 with SimpleBench across 5 shared models. Models that do well on LiveBench · Reasoning tend to do well on SimpleBench.
How often is LiveBench · Reasoning data refreshed?
BenchGecko pulls updates daily. New model scores on LiveBench · Reasoning appear as soon as they are published by Epoch AI or the model provider.
- Category
- Knowledge
- Max score
- 100
- Models
- 40
- Updated
- 2026-06-16
Top on LiveBench · Reasoning
GPT-5.1-Codex-Max · 84.6Qwen3.7 Max · 83.3Kimi K2.7 Code · 82.8DeepSeek V4 Pro · 82.7GPT-5.1-Codex · 82.0More knowledge benchmarks
Same category · related evaluations