Ebr Bench
The Frontier
Best score over time · one chart, every benchmark
Full rankings
21 models tested · sorted by score
| # | Model | Score |
|---|---|---|
| 1 | 76.2 | |
| 2 | 71.4 | |
| 3 | 57.1 | |
| 4 | 45.7 | |
| 5 | 44.8 | |
| 6 | 39.5 | |
| 7 | 30.5 | |
| 8 | 28.6 | |
| 9 | 25.4 | |
| 10 | 23.0 | |
| 11 | 19.1 | |
| 12 | 14.3 | |
| 13 | 14.3 | |
| 14 | 12.7 | |
| 15 | 12.7 | |
| 16 | 9.5 | |
| 17 | 9.5 | |
| 18 | 7.9 | |
| 19 | 4.8 | |
| 20 | 2.4 | |
| 21 | 2.4 |
Score distribution
Where models cluster
Correlated benchmarks
Pearson r · original research
Benchmarks that track with Ebr Bench
Pearson correlation across models scored on both benchmarks. Closer to 1 = strongly predictive.
Frequently asked
About Ebr Bench
What does Ebr Bench measure?
Ebr Bench is a knowledge benchmark in the BenchGecko catalog. 21 AI models have been tested on it. Scores range from 2.4 to 76.2 out of 100.
Which model leads on Ebr Bench?
GPT-6 Astra from OpenAI leads Ebr Bench with a score of 76.2. The median score across 21 tested models is 19.1.
Is Ebr Bench saturated?
No · the top score is 76.2 out of 100 (76%). There is still meaningful room for improvement on Ebr Bench.
Does Ebr Bench predict performance on other benchmarks?
Yes · Ebr Bench scores correlate 0.98 with Osworld 2 0 across 5 shared models. Models that do well on Ebr Bench tend to do well on Osworld 2 0.
How often is Ebr Bench data refreshed?
BenchGecko pulls updates daily. New model scores on Ebr Bench appear as soon as they are published by Epoch AI or the model provider.
- Category
- Knowledge
- Max score
- 100
- Models
- 21
- Updated
- 2026-09-22
Top on Ebr Bench
GPT-6 Astra · 76.2Claude Opus 5.5 · 71.4Claude Fable 5.1 · 57.1Claude Opus 5 · 45.7GPT-5.6 Sol · 44.8More knowledge benchmarks
Same category · related evaluations