GPT-5.1-Codex-Max
OpenAI·
LLMscodingcloud
Overview
Specialized ultra-high-performance coding model with breakthrough architecture.
Capabilities and innovations
Advanced code generationMulti-language masterySystem-level reasoningNeural Code SynthesisReal-time Code OptimizationIntegrated Debugging
Benchmarks
| Benchmark | Score | Source |
|---|---|---|
| GPQA Diamond | 89.7% | unsourced |
| Humanity’s Last Exam (no tools) | 38.2% | unsourced |
| SWE-bench Verified | 75.4% | unsourced |
| MMLU | 93.8% | unsourced |
- SWE-bench Pro: not reported by the vendor
- MMLU-Pro: not reported by the vendor
- Terminal-Bench 2.x: benchmark did not exist at release
- MMMU-Pro: benchmark did not exist at release
Links
More from OpenAI
Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.