Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Difficulty Correlation with Human Labels on Omni-Math n=1876

0.82Pearson Correlation

LLM compare

0.79920.80460.810.8154Dec 16, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2025.12
0.820.80.62
2025.12
0.80.780.6