GPT-5.3 Codex
OpenAI·
LLMscodingcloud
Overview
Agentic coding model, 25% faster, first model instrumental in creating itself.
Capabilities and innovations
Agentic coding25% fasterSelf-developingTool useSelf-DevelopmentTerminal-Bench SOTAOSWorld Leader
Benchmarks
| Benchmark | Score | Source |
|---|---|---|
| SWE-bench Pro | 56.8% | unsourced |
- GPQA Diamond: not reported by the vendor
- Humanity’s Last Exam (no tools): not reported by the vendor
- SWE-bench Verified: not reported by the vendor
- MMLU: not reported by the vendor
- MMLU-Pro: not reported by the vendor
- Terminal-Bench 2.x: not reported by the vendor
- MMMU-Pro: not reported by the vendor
Reliability
- Agentic tool use (τ-bench)
- 77.8% (higher is better)third party
Links
More from OpenAI
Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.