# ExploitBench — AI model rankings

A 'capability ladder' for security research, built by CMU researchers: the AI is given known bugs in Chrome's V8 engine and scored on how far it gets toward a working exploit inside a research sandbox — from understanding the patch to triggering a crash. Higher is better.

2 tracked models have a published ExploitBench score. Higher is better. Scores come from published lab reports and benchmark sources; recorded sources appear beside the scores.

## Ranking

| Rank | Model | Developer | Score | Source | Released |
| --- | --- | --- | --- | --- | --- |
| 1 | GPT-6 Astra | OpenAI | 100% | Lab | Sep 3 2026 |
| 2 | GLM-5.3 | Z.ai | 54.4% | Lab | Aug 14 2026 |


---

Canonical page: https://aireleasetracker.com/benchmark/exploitbench
Site index: https://aireleasetracker.com/llms.txt
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.