Building more with GPT-5.1-Codex-Max (OpenAI) 19 Nov 2025
GPT-5.1-Codex-Max
GPT-5.1-Codex-Max ranks first on 2 of the 25 benchmarks it has scores on.
OpenAI Released 19 Nov 2025
28
Benchmarks with a score
2
Ranked first, out of five or more models
5
In the top three
OpenAI Nov 2025
GPT-5.1-Codex-Max
Closed weights
No Epoch Capabilities Index score yet
- Terminal-Bench 2.0 60.5% #12 /43
- PostTrainBench 19.7% #10 /23
- SWE-Lancer 80% #2 /10
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ProofBench | 9.00% | #46 of 59 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| METR Time Horizon | 2.7 h | #2 of 31 | Official leaderboard | |
| OpenAI-Proof Q&A | 8.00% | #1 of 9 | Model card | |
| SWE-bench Verified | 77.9% | #28 of 150 | Model card | |
| SWE-Lancer | 80% | #2 of 10 | Model card | |
| OpenAI PRs | 53% | #3 of 12 | Model card | |
| ALE-Bench | 1,209 | #40 of 121 | Epoch AI | |
| METR Time Horizon 1.1 | 3.7 h | #9 of 26 | Official leaderboard | |
| Vibe Code Bench v1 | 22.2% | #6 of 17 | Official leaderboard | |
| IOI (Vals) | 21.4% | #22 of 55 | Official leaderboard | |
| PaperBench | 40% | #6 of 14 | Model card | |
| PostTrainBench | 19.7% | #10 of 23 | Official leaderboard | |
| MLE-bench | 17% | #9 of 18 | Model card | |
| OTelBench | 11.6% | #9 of 14 | Official leaderboard | |
| Vibe Code Bench | 22.2% | #80 of 115 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SnakeBench | 38 | #1 of 183 | Official leaderboard | |
| Terminal-Bench 2.0 | 60.5% | #12 of 43 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Coding prompt injections | 100% | #1 of 4 | Model card | |
| Tacit Knowledge and Troubleshooting | 77% | #9 of 29 | Model card | |
| StrongREJECT | 96.7% | #7 of 22 | Model card | |
| Capture the Flag (Professional) | 76% | #8 of 21 | Model card | |
| ProtocolQA Open-Ended | 35% | #13 of 25 | Model card | |
| Malware Refusals (Golden Set) | 100% | #2 of 3 | Model card | |
| CVE-Bench | 80% | #10 of 14 | Model card | |
| TroubleshootingBench | 29% | #15 of 19 | Model card | |
| Destructive action avoidance | 75% | #7 of 8 | Model card | |
| Multimodal Troubleshooting Virology | 38% | #26 of 26 | Model card | |
| Long-form Biological Risk Questions | 0% | #3 of 3 | Model card |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.
Its system card
Every result in the longer documents the lab published with it. 20 of them aren't in the launch post.
GPT-5.1-Codex-Max System Card 18 Nov 2025
Safety
Robustness
- StrongREJECT 96.7
- Coding prompt injections 100
Alignment
Bio and chem risk
Cyber risk
AI R&D risk
- SWE-Lancer 80
- PaperBench 40
- MLE-bench 17
- OpenAI PRs 53
- OpenAI-Proof Q&A 8