LiveBench · Mathematics
The Frontier
Best score over time · one chart, every benchmark
Full rankings
40 models tested · sorted by score
| # | Model | Score |
|---|---|---|
| 1 | 90.7 | |
| 2 | 89.8 | |
| 3 | 88.8 | |
| 4 | 85.3 | |
| 5 | 84.9 | |
| 6 | 84.3 | |
| 7 | 83.7 | |
| 8 | 83.7 | |
| 9 | 83.5 | |
| 10 | 81.1 | |
| 11 | 81.1 | |
| 12 | 80.5 | |
| 13 | 79.9 | |
| 14 | 79.7 | |
| 15 | 79.6 | |
| 16 | 79.6 | |
| 17 | 78.9 | |
| 18 | 78.4 | |
| 19 | 77.4 | |
| 20 | 77.0 | |
| 21 | 77.0 | |
| 22 | 76.3 | |
| 23 | 76.0 | |
| 24 | 74.4 | |
| 25 | 74.3 | |
| 26 | 73.9 | |
| 27 | 73.4 | |
| 28 | 70.4 | |
| 29 | 70.2 | |
| 30 | 68.9 | |
| 31 | 68.0 | |
| 32 | 64.7 | |
| 33 | 64.4 | |
| 34 | 64.0 | |
| 35 | 62.5 | |
| 36 | 54.5 | |
| 37 | 52.5 | |
| 38 | 37.0 | |
| 39 | 36.4 | |
| 40 | 36.0 |
Score distribution
Where models cluster
Correlated benchmarks
Pearson r · original research
Benchmarks that track with LiveBench · Mathematics
Pearson correlation across models scored on both benchmarks. Closer to 1 = strongly predictive.
Frequently asked
About LiveBench · Mathematics
What does LiveBench · Mathematics measure?
LiveBench · Mathematics is a knowledge benchmark in the BenchGecko catalog. 40 AI models have been tested on it. Scores range from 36.0 to 90.7 out of 100.
Which model leads on LiveBench · Mathematics?
DeepSeek V4 Pro from DeepSeek leads LiveBench · Mathematics with a score of 90.7. The median score across 40 tested models is 77.0.
Is LiveBench · Mathematics saturated?
No · the top score is 90.7 out of 100 (91%). There is still meaningful room for improvement on LiveBench · Mathematics.
Does LiveBench · Mathematics predict performance on other benchmarks?
Yes · LiveBench · Mathematics scores correlate 0.94 with SimpleBench across 5 shared models. Models that do well on LiveBench · Mathematics tend to do well on SimpleBench.
How often is LiveBench · Mathematics data refreshed?
BenchGecko pulls updates daily. New model scores on LiveBench · Mathematics 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 · Mathematics
DeepSeek V4 Pro · 90.7GLM 5.2 · 89.8GPT-5.2-Codex · 88.8Qwen3.7 Max · 85.3GLM 5.1 · 84.9More knowledge benchmarks
Same category · related evaluations