Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Theorem Autoformalization on FormalMATH
Loading...
4.47
Objects
FormalMATH
4.2465
4.35825
4.47
4.58175
Apr 24, 2026
Objects
Formulae
Formula Validity (FV)
Formula Quality (FQ)
Logical Soundness (LP)
Model Consistency (MC)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Objects
Formulae
Formula Validity (FV)
Formula Quality (FQ)
Logical Soundness (LP)
Model Consistency (MC)
FormalMATH
Size=5,560, Domain=Ol...
2026.04
4.47
4.53
97.5
80
98
96.5
Feedback
Search any
task
Search any
task
