Fortress
Distribution
Where models cluster
Correlated benchmarks
Pearson r · original research
Full rankings
3 models tested · sorted by score
| # | Model | Score |
|---|---|---|
| 1 |  Claude Opus 4.5 | 13.6 |
| 2 | Claude 3.5 Sonnet | 13.0 |
| 3 |  gpt-oss-120b | 8.2 |
Frequently asked
Pulled from the Fortress dataset · updated daily
What does Fortress measure?
Fortress is a knowledge benchmark in the BenchGecko catalog. 3 AI models have been tested on it. Scores range from 8.2 to 13.6 out of 100.
Which model leads on Fortress?
Claude Opus 4.5 from Anthropic leads Fortress with a score of 13.6. The median score across 3 tested models is 13.0.
Is Fortress saturated?
No · the top score is 13.6 out of 100 (14%). There is still meaningful room for improvement on Fortress.
What makes Fortress distinctive?
Fortress is a knowledge benchmark with limited overlap to the rest of the catalog · it measures capabilities that are not well-covered by other benchmarks we track.
How often is Fortress data refreshed?
BenchGecko pulls updates daily. New model scores on Fortress appear as soon as they are published by Epoch AI or the model provider.
More knowledge benchmarks
Same category · related evaluations