PatchBench (OpenAI)
Models patch security flaws. Automated tests and model-based review check that each patch fixes the flaw, keeps the intended behavior and is ready to merge.
Lab-created in-house eval (OpenAI), used for its Codex Security patch skill. Only OpenAI reports scores. Not the academic PatchBench (arXiv 2609.04075), which patches C and C++ vulnerabilities.
- Made by
- OpenAI
- Released
- November 2026
- Kind
- Secure code and review
- Level
- Expert
- Scored
- Graded by a model
- Answers
- Agent task
- Tasks
- Kept private
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Items from
- Written by experts
- Refresh
- One fixed set
- Run by
- A model developer
- In views
- Lab internal evals
- Strongest model tested
- GPT-6.2 Astra #1 on the capability index
- Last in a launch post
- November 2026
- Last model added
- November 2026
GPT-6.2 Astra leads with 79.7%
Best score per model as labs report them in their own cards, drawn striped. Labs pick their own settings, so these compare less cleanly than independent runs.
- 1 GPT-6.2 Astra 79.7%
- 2 GPT-6.2 Sol 75.6%
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-6.2 Astra | 79.7% | Nov 2026 | Lab model card | |
| 2 | GPT-6.2 Sol | 75.6% | Nov 2026 | Lab model card |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Labs’ model cards
One lab put it in a launch post in the last six months
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Nov 17, 2026 | GPT-6.2 Sol | 75.6 | PatchBench (GPT-6.2 Sol Max) |
| Nov 17, 2026 | GPT-6.2 Astra | 79.7 | PatchBench (GPT-6.2 Astra Xhigh and Max) |
More in Cybersecurity
- ExploitGym In use 869 real-vulnerability exploit-development tasks (userspace, V8, Linux kernel). Success means capturing a flag through the intended vulnerability. GPT-6 Astra 42.4%
- ExploitBench In use 41 recent V8 JavaScript-engine N-day vulnerabilities. Progress measured by 16 grader-verified capability flags across five tiers. GPT-6 Astra 100%
- ExploitBench - Internal Port In use Agents develop working exploits for recently disclosed vulnerabilities to limit contamination. Scored as arbitrary code execution success rate. GPT-6.2 Astra 53.5%
- Atomic Challenges In use Agents solve 22 skill-level offensive security challenges in vulnerability research, network attack simulation and evasion. Scored as challenges solved. GPT-6 Astra 90.9%
- MiMo Cyber Bench In use Agents do in-house cybersecurity tasks that add to public vulnerability reproduction and exploitation benchmarks. The report gives no task count or grading details. MiMo-V2.6 Pro 81.7%
- SecureSWE (OpenAI) In use Models write functional and secure code for security-sensitive components, such as serving files or handling database queries. OpenAI has not published the task count or grading. GPT-6.2 Astra 65.7%
Data audit
4 of 5 checks pass, 1 warning. Look first at the Confidence check. Likely. Some facts rest on secondary sources. Every benchmark
Catalog record 1 warning 1 pass
- Pass Task access The tasks are private.
- Warning Confidence Likely. Some facts rest on secondary sources.
Scores 2 pass 3 notes
- Note Independent runs Only labs’ own numbers, as expected for an in-house eval. Scores from launch posts (2 scores).
- Note Models scored Only 2 models we track.
- Pass Newest score The newest is from November 2026, for GPT-6.2 Astra.
- Note Frontier models 1 of the top 10 has a score, which is fine for an in-house eval. The strongest tested is GPT-6.2 Astra (#1).
- Pass Headroom The best is 79.7%, under 85%, so it still separates models.
Leaderboard import 1 note
- Note Importer No public leaderboard to read.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.