Surface Evolver Bench
The Frontier
Best score over time · one chart, every benchmark
Full rankings
21 models tested · sorted by score
| # | Model | Score |
|---|---|---|
| 1 | 95.0 | |
| 2 | 95.0 | |
| 3 | 93.1 | |
| 4 | 87.5 | |
| 5 | 83.8 | |
| 6 | 76.9 | |
| 7 | 74.4 | |
| 8 | 61.9 | |
| 9 | 60.0 | |
| 10 | 58.1 | |
| 11 | 55.6 | |
| 12 | 55.0 | |
| 13 | 52.5 | |
| 14 | 48.8 | |
| 15 | 46.3 | |
| 16 | 45.0 | |
| 17 | 44.4 | |
| 18 | 40.0 | |
| 19 | 30.6 | |
| 20 | 26.9 | |
| 21 | 25.0 |
Score distribution
Where models cluster
Correlated benchmarks
Pearson r · original research
Benchmarks that track with Surface Evolver Bench
Pearson correlation across models scored on both benchmarks. Closer to 1 = strongly predictive.
Frequently asked
About Surface Evolver Bench
What does Surface Evolver Bench measure?
Surface Evolver Bench is a knowledge benchmark in the BenchGecko catalog. 21 AI models have been tested on it. Scores range from 25.0 to 95.0 out of 100.
Which model leads on Surface Evolver Bench?
Claude Fable 5 from Anthropic leads Surface Evolver Bench with a score of 95.0. The median score across 21 tested models is 55.6.
Is Surface Evolver Bench saturated?
No · the top score is 95.0 out of 100 (95%). There is still meaningful room for improvement on Surface Evolver Bench.
Does Surface Evolver Bench predict performance on other benchmarks?
Yes · Surface Evolver Bench scores correlate 0.96 with Ebr Bench across 5 shared models. Models that do well on Surface Evolver Bench tend to do well on Ebr Bench.
How often is Surface Evolver Bench data refreshed?
BenchGecko pulls updates daily. New model scores on Surface Evolver Bench appear as soon as they are published by Epoch AI or the model provider.
- Category
- Knowledge
- Max score
- 100
- Models
- 21
- Updated
- 2026-09-10
Top on Surface Evolver Bench
Claude Fable 5 · 95.0Kimi K3 · 95.0GPT-5.6 Sol · 93.1Claude Opus 4.8 · 87.5GPT-5.6 Terra · 83.8More knowledge benchmarks
Same category · related evaluations