Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Capture the Flag on CTF-Dojo
Loading...
50.2
Pass@1
Full System
11.096
21.248
31.4
41.552
Jun 1, 2026
Pass@1
Updated 1d ago
Evaluation Results
Method
Method
Links
Pass@1
Full System
System Category=Ours
2026.06
50.2
Multi agent
System Category=Ours
2026.06
47.9
Adaptive
System Category=Ours
2026.06
46
A-Evolve
System Category=Auto-h...
2026.06
45.2
GEPA
System Category=Auto-h...
2026.06
42.9
Meta Harness
System Category=Auto-h...
2026.06
41
OctoTools
System Category=Human
2026.06
38.3
Sonnet
System Category=No evo...
2026.06
37.2
SkillOS
System Category=Auto-h...
2026.06
29.5
DeepSeek
System Category=No evo...
2026.06
26.1
Cont. Harness
System Category=Auto-h...
2026.06
25.7
Kimi
System Category=No evo...
2026.06
24.5
Haiku
System Category=No evo...
2026.06
23.8
GLM
System Category=No evo...
2026.06
12.6
Feedback
Search any
task
Search any
task