evals.report
BenchmarksLabsCompareRun guidesIn the wild
Models
1 selected
MiniMax M2.1MiniMax
Benchmarks
3 selected
SWE-bench VerifiedCodingDeepSWECodingSWE-bench ProCoding
BenchmarkMiniMax M2.1OpenMiniMax
SWE-bench Verified% resolved
DeepSWE% resolved
SWE-bench Pro% resolved36.81%
% resolved
% resolved
36.81%

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