evals.report
BenchmarksLabsCompareRun guides
Models
1 selected
Claude Opus 4.6 thinkingAnthropic
Benchmarks
2 selected
SWE-bench VerifiedCodingGPQA DiamondReasoning
BenchmarkClaude Opus 4.6 thinkingAnthropic
SWE-bench Verified% resolved
GPQA Diamondaccuracy
SWE-bench Verified
% resolved
Claude Opus 4.6 thinking · Anthropic
GPQA Diamond
accuracy
Claude Opus 4.6 thinking · Anthropic

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