evals.report
BenchmarksLabsCompareRun guides
Models
1 selected
Kimi K2.5Moonshot AI
Benchmarks
2 selected
SWE-bench VerifiedCodingGPQA DiamondReasoning
BenchmarkKimi K2.5Moonshot AI
SWE-bench Verified% resolved73.8%
GPQA Diamondaccuracy87.6%
SWE-bench Verified
% resolved
Kimi K2.5 · Moonshot AI
73.8%
GPQA Diamond
accuracy
Kimi K2.5 · Moonshot AI
87.6%

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