Reference
Compare models
Select models and benchmarks. Scores are shown exactly within each benchmark’s own metric — never combined into an aggregate, average, or winner.
Models
1 selected
Fugu UltraSakana AI
Benchmarks
3 selected
SWE-bench VerifiedCodingDeepSWECodingSWE-bench ProCoding
| Benchmark | Fugu UltraSakana AI |
|---|---|
| SWE-bench Verified% resolved | — |
| DeepSWE% resolved | — |
| SWE-bench Pro% resolved | 73.7% |
% resolved
% resolved
% resolved
73.7%
No aggregate score is calculated. Each row uses its benchmark’s own metric. Compare rows independently.