evals.report
BenchmarksLabsCompareRun guidesIn the wild
Models
1 selected
Muse WonderMeta
Benchmarks
3 selected
SWE-bench VerifiedCodingDeepSWECodingSWE-bench ProCoding
BenchmarkMuse WonderMeta
SWE-bench Verified% resolved—
DeepSWE% resolved78.8%
SWE-bench Pro% resolved—

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