ExploitGym (version unspecified; token-budgeted): leaderboard
Approximate counts of successful intended-vulnerability exploits on token-budgeted ExploitGym runs. The native rows omit a structured version field; their source notes identify the v1 implementation on 869 challenges, offline with runtime package installation disabled. Counts are converted from published per-attempt rates multiplied by 869 and remain approximate. The runs have no wall-clock cap, and the exact output-token limit is not stated. They remain separate from time-limited evaluations.
Metric: Successful intended exploits (#); version unspecified; token-budgeted. Source: www.cybergym.io. Saturation forecast: Around 2029. 2 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra | 368 | #3 |
| 2 | GPT-6.1 Sol | 305 | #6 |
No result here: #2 Claude Opus 5.5, #8 Gemini 4 Argon, #9 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=exploitgym-version-unspecified-token-budgeted · How It Works · Data refreshed daily, snapshot 2026-10-28.