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-5.3-CodexOpenAI
Benchmarks
2 selected
SWE-bench VerifiedCodingGPQA DiamondReasoning
| Benchmark | GPT-5.3-CodexOpenAI |
|---|---|
| SWE-bench Verified% resolved | 74.8% |
| GPQA Diamondaccuracy | — |
SWE-bench Verified
% resolved
GPT-5.3-Codex · OpenAI
74.8%
GPQA Diamond
accuracy
GPT-5.3-Codex · OpenAI
—
No aggregate score is calculated. Each row uses its benchmark’s own metric. Compare rows independently.