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
DeepSeek V3.1DeepSeek
Benchmarks
3 selected
SWE-bench VerifiedCodingDeepSWECodingSWE-bench ProCoding
| Benchmark | DeepSeek V3.1DeepSeek |
|---|---|
| SWE-bench Verified% resolved | 66.0% |
| DeepSWE% resolved | — |
| SWE-bench Pro% resolved | — |
% resolved
66.0%
% resolved
% resolved
No aggregate score is calculated. Each row uses its benchmark’s own metric. Compare rows independently.