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

HS Competition

Benchmarks

Task NameDataset NameSOTA ResultTrend
Automated Theorem ProvingHS Competition Plane Geometry 1.0 (test)
Thousands of Output Tokens0.16
6
Formal Theorem ProvingHS Competition (10)
Proof Length17.8
5
Showing 2 of 2 rows