Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Adversarial Detection on Expanded benchmark Arithmetic error
Loading...
19
Caught Rate
Theoria
18.05
18.525
19
19.475
Jul 1, 2026
Caught Rate
Detection Rate
Updated 24d ago
Evaluation Results
Method
Method
Links
Caught Rate
Detection Rate
Theoria
Model=GPT-5.5, Web sea...
2026.07
19
95
Holistic judge
Model=GPT-5.5, Web sea...
2026.07
19
95
Feedback
Search any
task
Search any
task