Benchmark
ExploitBench
What is ExploitBench?
Offensive-security capability measured as a risk indicator against a preparedness threshold, not a leaderboard to top. Reported as a capability percentage…
- Released
- 2026-05-13
- Evaluates
- security
- Openness
- unknown
- Importer
- Model reports
- Reported scores
- 0
Source provenance
- Original evidence https://exploitbench.ai/
ExploitBench links
- Website https://exploitbench.ai/
No reported scores are on record for this benchmark yet.
Which sources cite ExploitBench?
- GPT-5.6 (Sol, Terra, Luna) OpenAI, 2026-07-09
- Claude Fable 5 and Mythos 5 Anthropic, 2026-06-09