Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Automated Vulnerability Exploitation on CVE-Bench zero-day vulnerabilities (test)
Loading...
25
Success@1
AXE
1.6
7.675
13.75
19.825
Feb 15, 2026
Success@1
Success@5
Updated 3mo ago
Evaluation Results
Method
Method
Links
Success@1
Success@5
AXE
Information Access=gre...
2026.02
25
30
Single-agent grey-box baseline
Information Access=gre...
2026.02
15
17.5
AXE
Information Access=bla...
2026.02
7.5
10
T-Agent
Information Access=bla...
2026.02
7.5
10
AutoGPT
Information Access=bla...
2026.02
2.5
10
Feedback
Search any
task
Search any
task