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

Factual Recall on Factual (test)

0.756AUROC

Post-solution probe

0.69360.70980.7260.7422Jul 8, 2026
Updated 16d ago

Evaluation Results

MethodLinks
2026.07
0.7560.104-
2026.07
0.7310.133-
2026.07
0.6960.161-