Ebr Bench
The Frontier
Best score over time · one chart, every benchmark
Full rankings
30 models tested · sorted by score
| # | Model | Score |
|---|---|---|
| 1 | 90.5 | |
| 2 | 87.6 | |
| 3 | 78.1 | |
| 4 | 76.2 | |
| 5 | 71.4 | |
| 6 | 64.8 | |
| 7 | 57.1 | |
| 8 | 54.3 | |
| 9 | 53.3 | |
| 10 | 45.7 | |
| 11 | 44.8 | |
| 12 | 43.8 | |
| 13 | 39.5 | |
| 14 | 34.3 | |
| 15 | 30.5 | |
| 16 | 28.6 | |
| 17 | 25.4 | |
| 18 | 23.0 | |
| 19 | 19.1 | |
| 20 | 18.1 | |
| 21 | 14.3 | |
| 22 | 14.3 | |
| 23 | 12.7 | |
| 24 | 12.7 | |
| 25 | 9.5 | |
| 26 | 9.5 | |
| 27 | 7.9 | |
| 28 | 4.8 | |
| 29 | 2.4 | |
| 30 | 2.4 |
What it measures · how it is scored · sources · as of 2026-11-17
- How it is scored · Scored as a percentage · higher is better · maximum 100
- Released · 2026-07-01
- Scores from · Epoch AI Benchmarking Hub (30 scores)
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. 30 AI models have been tested on it. Scores range from 2.4 to 90.5 out of 100.
Which model leads on Ebr Bench?
Claude Fable 5.2 from Anthropic leads Ebr Bench with a score of 90.5. The median score across 30 tested models is 29.5.
Is Ebr Bench saturated?
No · the top score is 90.5 out of 100 (90%). There is still meaningful room for improvement on Ebr Bench.
Does Ebr Bench predict performance on other benchmarks?
Yes · Ebr Bench scores correlate 0.94 with Furniture Assembly across 20 shared models. Models that do well on Ebr Bench tend to do well on Furniture Assembly.
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
- 30
- Updated
- 2026-11-10
Top on Ebr Bench
Claude Fable 5.2 · 90.5Gemini 4 Carbon · 87.6GPT-6.1 Terra · 78.1GPT-6 Astra · 76.2Claude Opus 5.5 · 71.4More knowledge benchmarks
Same category · related evaluations