ExploitBench - Internal Port
Agents develop working exploits for recently disclosed vulnerabilities to limit contamination. Scored as arbitrary code execution success rate.
OpenAI internal port of ExploitBench with June to August 2026 vulnerabilities.
- Made by
- OpenAI
- Released
- September 2026
- Kind
- Finding and exploiting real bugs
- Level
- Research frontier
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- Kept private
- Measures
- Capability
- Risk
- Cyber offence
- Language
- English
- Interaction
- Agentic
- Environment
- Terminal
- Items from
- Another benchmark, Real work and use
- Refresh
- One fixed set
- Run by
- A model developer
- Based on
- ExploitBench
- 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 53.5%
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 53.5%
- 2 GPT-6.2 Sol 50.5%
- 3 GPT-6 Cyber 42%
- 4 GPT-6.1 Terra 24.5%
- 5 GPT-6.1 Sol 21.5%
- 6 GPT-6 Sol 5.50%
- 7 GPT-6 Luna 0%
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-6.2 Astra | 53.5% | Nov 2026 | Lab model card | |
| 2 | GPT-6.2 Sol | 50.5% | Nov 2026 | Lab model card | |
| 3 | GPT-6 Cyber | 42% | Nov 2026 | Lab model card | |
| 4 | GPT-6.1 Terra | 24.5% | Oct 2026 | Lab model card | |
| 5 | GPT-6.1 Sol | 21.5% | Sep 2026 | Lab model card | |
| 6 | GPT-6 Sol | 5.50% | Sep 2026 | Lab model card | |
| 7 | GPT-6 Luna | 0% | Sep 2026 | Lab model card |
5 models have held number one in labs’ own numbers since its release in September 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Labs’ model cards
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. OpenAI accounts for 8 of the 8 releases that named it since 2024.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Nov 17, 2026 | GPT-6.2 Sol | 50.5 | ExploitBench Internal Port (June to August 2026), success rate (GPT-6.2 Sol Max, safeguards and classifiers disabled) |
| Nov 17, 2026 | GPT-6.2 Astra | 53.5 | ExploitBench Internal Port (June to August 2026), success rate (GPT-6.2 Astra Max, safeguards and classifiers disabled) |
| Nov 5, 2026 | GPT-6 Cyber | 42 | ExploitBench Internal Port, mean arbitrary code-execution success rate across V8 and Chrome targets, June to August 2026 |
8 system cards report it, from 1 lab
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Nov 17, 2026 | GPT-6.2 Sol system card | 50.5 | ExploitBench Internal Port (June to August 2026), mean arbitrary code execution rate across V8 and Chrome, maximum reasoning setting (Table 4) | Cyber risk |
| Nov 17, 2026 | GPT-6.2 Astra system card | 53.5 | ExploitBench Internal Port (June to August 2026), mean arbitrary code execution rate across V8 and Chrome, maximum reasoning setting (Table 4) | Cyber risk |
| Nov 5, 2026 | GPT-6 Cyber system card | 42 | ExploitBench Internal Port, mean arbitrary code-execution success rate across V8 and Chrome targets, June to August 2026 | Cyber risk |
| Oct 26, 2026 | GPT-6.1 Terra system card addendum | 24.5 | ExploitBench - Internal Port (June–August 2026), arbitrary code-execution success rate (9.0.2.2) | Cyber risk |
| Sep 29, 2026 | GPT-6.1 Sol system card addendum | 21.5 | ExploitBench - Internal Port (June–August 2026), arbitrary code-execution success rate (9.1.2.2) | Cyber risk |
| Sep 22, 2026 | GPT-6 Sol system card | 5.5 | ExploitBench - Internal Port (June–August 2026), maximum success rate (A.8.1.2.2) | Cyber risk |
| Sep 22, 2026 | GPT-6 Luna system card | 0 | ExploitBench - Internal Port (June–August 2026), text says no challenge completed (A.8.1.2.2) | Cyber risk |
| Sep 3, 2026 | GPT-6 Astra system card | ExploitBench - Internal Port (June–August 2026), success rate vs output tokens, chart without printed numbers (Figure 47) | Cyber risk |
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%
- 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%
- PatchBench (OpenAI) In use 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. GPT-6.2 Astra 79.7%
- 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
All 7 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access The tasks are private.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Note Independent runs Only labs’ own numbers, as expected for an in-house eval. Scores from launch posts (3 scores) and system cards (7 scores).
- Pass Models scored 7 models we track.
- Pass Newest score The newest is from November 2026, for GPT-6.2 Astra.
- Pass Frontier models 3 of the top 10 have a score, led by GPT-6.2 Astra (#1).
- Pass Headroom The best is 53.5%, 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.