Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Counterexample Generation on SAIR hard3 Official (n=20)
Loading...
65.3
Accuracy
AN38
55.108
57.754
60.4
63.046
Apr 20, 2026
Accuracy
Accuracy Delta vs Baseline
F1 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Accuracy Delta vs Baseline
F1 Score
AN38
Variant=AN38, Backbone...
2026.04
65.3
5.6
67.6
Baseline
Variant=no cheatsheet,...
2026.04
56.3
-
53
AN45c
Variant=AN45c, Backbon...
2026.04
55.5
4.3
63.7
Feedback
Search any
task
Search any
task
