Skip to main content
leaderboard
.cn
Toggle Sidebar
Search models or organizations…
⌘K
Explore
Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio
Library
Models
Pricing
Organizations
Benchmarks
Data sources
Settings
Toggle Sidebar
leaderboard
.cn
Loading page content
Feedback
Benchmark details loading
Back to benchmarks
ExploitBench (ACE-normalized)
Cybersecurity
Agents
Share
Official website
Mean exploit capability normalized to arbitrary code execution. Historical vulnerabilities may cause contamination; not an ACE success rate.
Ranking
Sources
#
Model
Score
1
GPT-6 Astra
OpenAI
100.0
%
2
GPT-6.1 Terra
OpenAI
97.1
%
2 models total