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
GPT-4oOpenAI
Benchmarks
2 selected
SWE-bench VerifiedCodingGPQA DiamondReasoning
| Benchmark | GPT-4oOpenAI |
|---|---|
| SWE-bench Verified% resolved | 31.0% |
| GPQA Diamondaccuracy | 49.2% |
SWE-bench Verified
% resolved
GPT-4o · OpenAI
31.0%
GPQA Diamond
accuracy
GPT-4o · OpenAI
49.2%
No aggregate score is calculated. Each row uses its benchmark’s own metric. Compare rows independently.