evals.report
BenchmarksLabsCompareRun guides
Models
1 selected
Claude Opus 4.5Anthropic
Benchmarks
2 selected
SWE-bench VerifiedCodingGPQA DiamondReasoning
BenchmarkClaude Opus 4.5Anthropic
SWE-bench Verified% resolved76.7%
GPQA Diamondaccuracy86.0%
SWE-bench Verified
% resolved
Claude Opus 4.5 · Anthropic
76.7%
GPQA Diamond
accuracy
Claude Opus 4.5 · Anthropic
86.0%

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