Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Formal Theorem Proving on miniF2F (Success Rate)

66.31Proof Success Rate

Segment-level

52.155655.830359.50563.1797May 12, 2026
Updated 21d ago

Evaluation Results

MethodLinks
2026.05
66.31
2026.05
64.84
2026.05
63.52
2026.05
63.11
2026.05
63.11
2026.05
61.64
2026.05
60.9
2026.05
59.02
2026.05
55.9
2026.05
54.67
2026.05
54.51
2026.05
52.7