Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Black-box system prompt extraction on 41 Models Open-weight
Loading...
2.4
Avg Turns
JUSTASK
2.28
2.34
2.4
2.46
Jan 29, 2026
Avg Turns
Success Rate
Updated 3mo ago
Evaluation Results
Method
Method
Links
Avg Turns
Success Rate
JUSTASK
Models=23, Primary Ski...
2026.01
2.4
100
Feedback
Search any
task
Search any
task