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-5.4 xHighOpenAI
Benchmarks
2 selected
SWE-bench VerifiedCodingGPQA DiamondReasoning
| Benchmark | GPT-5.4 xHighOpenAI |
|---|---|
| SWE-bench Verified% resolved | — |
| GPQA Diamondaccuracy | 93.3% |
SWE-bench Verified
% resolved
GPT-5.4 xHigh · OpenAI
—
GPQA Diamond
accuracy
GPT-5.4 xHigh · OpenAI
93.3%
No aggregate score is calculated. Each row uses its benchmark’s own metric. Compare rows independently.