Introducing GPT-5.2-Codex (OpenAI) 18 Dec 2025
GPT-5.2 Codex
GPT-5.2 Codex places in the top three on 3 benchmarks.
OpenAI Released 18 Dec 2025
31
Benchmarks with a score
0
Ranked first, out of five or more models
3
In the top three
OpenAI Dec 2025
GPT-5.2 Codex
Closed weights
No Epoch Capabilities Index score yet
- SWE-Bench Pro 41% #11 /24
- Terminal-Bench 2.0 66.5% #7 /43
- PostTrainBench 17.2% #14 /23
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.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Wer wird Millionär? LLM Benchmark | 200000.0 | #12 of 76 | Official leaderboard | |
| BullshitBench | 36.4% | #42 of 107 | Official leaderboard | |
| BullshitBench V2 | 45% | #53 of 122 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenAI PRs | 55% | #2 of 12 | Model card | |
| SWE-bench Verified | 72.8% | #11 of 60 | Official leaderboard | |
| OpenAI-Proof Q&A | 8.00% | #2 of 9 | Model card | |
| ALE-Bench | 1,300 | #34 of 121 | Epoch AI | |
| SlopCodeBench | 21.9% | #4 of 14 | Official leaderboard | |
| OpenHands Index | 58.3% | #11 of 33 | Official leaderboard | |
| PaperBench | 43% | #5 of 14 | Model card | |
| OTelBench | 15.9% | #6 of 14 | Official leaderboard | |
| SWE-Bench Pro | 41% | #11 of 24 | Official leaderboard | |
| Vibe Code Bench | 37.9% | #68 of 115 | Official leaderboard | |
| PostTrainBench | 17.2% | #14 of 23 | Official leaderboard | |
| SWE-bench Multilingual | 66.3% | #10 of 13 | Official leaderboard | |
| WebDev Arena | 1,339 | #84 of 105 | Epoch AI | |
| Code Arena | 1,339 | #101 of 124 | Official leaderboard | |
| MLE-bench | 10% | #16 of 18 | Model card |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SnakeBench | 32 | #23 of 183 | Official leaderboard | |
| Terminal-Bench 2.0 | 66.5% | #7 of 43 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BinaryAudit | 45.6% | #3 of 20 | Official leaderboard | |
| Capture the Flag (Professional) | 88.1% | #4 of 21 | Model card | |
| ProtocolQA Open-Ended | 39% | #8 of 25 | Model card | |
| StrongREJECT | 93.3% | #9 of 22 | Model card | |
| Tacit Knowledge and Troubleshooting | 73% | #12 of 29 | Model card | |
| CVE-Bench | 87% | #6 of 14 | Model card | |
| TroubleshootingBench | 34% | #11 of 19 | Model card | |
| Cyber Range | 72.7% | #6 of 10 | Model card | |
| Destructive action avoidance | 76% | #6 of 8 | Model card | |
| Multimodal Troubleshooting Virology | 48% | #21 of 26 | Model card | |
| CyScenarioBench | 0% | #12 of 14 | 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. 16 of them aren't in the launch post.
Addendum to GPT-5.2 System Card: GPT-5.2-Codex 18 Dec 2025
Safety
Robustness
- StrongREJECT 93.3
Alignment
Bio and chem risk
Cyber risk
AI R&D risk
- OpenAI PRs 55
- MLE-bench 10
- PaperBench 43
- OpenAI-Proof Q&A 8