SWE-Bench Pro (Private)
Full rankings
2 models tested · sorted by score
| # | Model | Score |
|---|---|---|
| 1 | 23.4 | |
| 2 | 10.1 |
Score distribution
Where models cluster
Correlated benchmarks
Pearson r · original research
Frequently asked
About SWE-Bench Pro (Private)
What does SWE-Bench Pro (Private) measure?
SWE-Bench Pro (Private) is a knowledge benchmark in the BenchGecko catalog. 2 AI models have been tested on it. Scores range from 10.1 to 23.4 out of 100.
Which model leads on SWE-Bench Pro (Private)?
Claude Opus 4.5 from Anthropic leads SWE-Bench Pro (Private) with a score of 23.4. The median score across 2 tested models is 16.8.
Is SWE-Bench Pro (Private) saturated?
No · the top score is 23.4 out of 100 (23%). There is still meaningful room for improvement on SWE-Bench Pro (Private).
What makes SWE-Bench Pro (Private) distinctive?
SWE-Bench Pro (Private) 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 SWE-Bench Pro (Private) data refreshed?
BenchGecko pulls updates daily. New model scores on SWE-Bench Pro (Private) appear as soon as they are published by Epoch AI or the model provider.
- Category
- Knowledge
- Max score
- 100
- Models
- 2
- Updated
- 2025-11-24
More knowledge benchmarks
Same category · related evaluations