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
ExploitGym
Cybersecurity
Agents
Share
Results for 16 models collected from 7 public sources.
Ranking
Sources
#
Model
Score
1
GPT-6 Astra
OpenAI
42.4
%
2
GPT-6.1 Sol
OpenAI
35.1
%
3
GPT-5.6 Sol
OpenAI
33.7
%
4
Claude Fable 5.1
Anthropic
30.4
%
5
Claude Fable 5
Anthropic
28.4
%
6
GPT-5.6 Terra
OpenAI
23.2
%
7
GPT-6 Sol
OpenAI
22.1
%
8
Claude Opus 5
Anthropic
22.1
%
9
Kimi K3.1 Pro
Moonshot AI
20.7
%
10
MiMo-V2.6-Pro
Xiaomi
17.8
%
16 models total
1
2
