Reference
Compare models
Select models and benchmarks. Scores are shown exactly within each benchmark’s own metric — never combined into an aggregate, average, or winner.
Models
1 selected
Claude 3.7 SonnetAnthropic
Benchmarks
2 selected
SWE-bench VerifiedCodingGPQA DiamondReasoning
| Benchmark | Claude 3.7 SonnetAnthropic |
|---|---|
| SWE-bench Verified% resolved | 61.0% |
| GPQA Diamondaccuracy | 78.5% |
SWE-bench Verified
% resolved
Claude 3.7 Sonnet · Anthropic
61.0%
GPQA Diamond
accuracy
Claude 3.7 Sonnet · Anthropic
78.5%
No aggregate score is calculated. Each row uses its benchmark’s own metric. Compare rows independently.