VulnGym (Hard): leaderboard
Metric: Advisory recall (%; share of the 31 advisories with at least one reference vulnerability entry whose entry point and critical operation the agent both localizes, end-to-end detection from the advisory title and description; Hard level of VulnGym (reference traces of 9 or more steps: 31 GitHub advisories, 46 vulnerability entries); read-only shell commands; locations match within 5 lines of the same repository-relative path). Source: arxiv.org. Saturation forecast: Around 2029. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V4 Flash | 22.58 |
| 2 | MiniMax-M3 | 16.13 |
| 3 | GLM-5.2 | 16.13 |
Interactive version: theaggregate.ai/benchmark?slug=vulngym-hard · How It Works · Data refreshed daily, snapshot 2026-09-29.