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

Formal Theorem Proving on NuminaMath LEAN (In-domain)

1,707.19Average Token Cost

Segment-level

1,293.27484,087.20246,881.139,675.0576May 12, 2026
Updated 21d ago

Evaluation Results

MethodLinks
2026.05
1,707.1916.46
2026.05
3,280.9337.45
2026.05
5,246.8753.27
2026.05
12,055.0748.07