0

ExploitBench

Saturated

Offensive-cybersecurity exploitation benchmark.

Domain
cybersecurity
Published
Jun 2026
Notable for
Cybersecurity exploitation benchmark used at Claude Fable 5 launch.

Cite

Notes

Only stored in your browser.

Attribution

Leaderboard scores
AnthropicOpenAI
Attribution policy →

Top score 100.0% by GPT-6 Astra - 5 models reporting (5 frontier)

Score history

4
25%44%63%81%100%Apr 26Jun 26Aug 26GPT-5.5Claude Opus 4.8Claude Fable 5GPT-6 Astra

Top models

5
ExploitBenchBar chart with 5 bars. Highest value: GPT-6 Astra at 100.
5 models

FAQ

What is ExploitBench?
Offensive-cybersecurity exploitation benchmark.
What is the current top score on ExploitBench?
The top reported score is 100.0% by GPT-6 Astra, across 5 models reporting (5 from frontier labs).