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
DeepSeek R1DeepSeek
Benchmarks
2 selected
SWE-bench VerifiedCodingGPQA DiamondReasoning
| Benchmark | DeepSeek R1DeepSeek |
|---|---|
| SWE-bench Verified% resolved | — |
| GPQA Diamondaccuracy | 69.2% |
SWE-bench Verified
% resolved
DeepSeek R1 · DeepSeek
—
GPQA Diamond
accuracy
DeepSeek R1 · DeepSeek
69.2%
No aggregate score is calculated. Each row uses its benchmark’s own metric. Compare rows independently.