Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Counterexample Generation on SAIR hard3 Local (n=400)
Loading...
79.25
Accuracy
AN45c
58.97
64.235
69.5
74.765
Apr 20, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
AN45c
Variant=AN45c, Backbon...
2026.04
79.25
AN38
Variant=AN38, Backbone...
2026.04
71.8
Baseline
Variant=no cheatsheet,...
2026.04
59.75
Feedback
Search any
task
Search any
task