SWE Atlas · Test Writing
Distribution
Where models cluster
Correlated benchmarks
Pearson r · original research
Full rankings
2 models tested · sorted by score
| # | Model | Score |
|---|---|---|
| 1 |  Claude Opus 4.6 (Fast) | 36.7 |
| 2 | Claude Sonnet 4.6 | 31.8 |
Frequently asked
Pulled from the SWE Atlas · Test Writing dataset · updated daily
What does SWE Atlas · Test Writing measure?
SWE Atlas · Test Writing is a knowledge benchmark in the BenchGecko catalog. 2 AI models have been tested on it. Scores range from 31.8 to 36.7 out of 100.
Which model leads on SWE Atlas · Test Writing?
Claude Opus 4.6 (Fast) from Anthropic leads SWE Atlas · Test Writing with a score of 36.7. The median score across 2 tested models is 34.2.
Is SWE Atlas · Test Writing saturated?
No · the top score is 36.7 out of 100 (37%). There is still meaningful room for improvement on SWE Atlas · Test Writing.
What makes SWE Atlas · Test Writing distinctive?
SWE Atlas · Test Writing 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 Atlas · Test Writing data refreshed?
BenchGecko pulls updates daily. New model scores on SWE Atlas · Test Writing appear as soon as they are published by Epoch AI or the model provider.
More knowledge benchmarks
Same category · related evaluations