evals.report
BenchmarksLabsCompareRun guidesIn the wild
Models
1 selected
GPT-5OpenAI
Benchmarks
3 selected
SWE-bench VerifiedCodingDeepSWECodingSWE-bench ProCoding
BenchmarkGPT-5OpenAI
SWE-bench Verified% resolved73.6%
DeepSWE% resolved
SWE-bench Pro% resolved41.78%
% resolved
% resolved
41.78%

No aggregate score is calculated. Each row uses its benchmark’s own metric. Compare rows independently.