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

Reinforcement Learning on IDP v4

75,033,713Average Return

ANN

-2,904,138.6817,329,726.6637,563,59257,797,457.34Feb 1, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
75,033,713
2026.02
38,594,440
2026.02
93,541
2026.02
93,521
2026.02
93,511
2026.02
93,501
2026.02
93,481
2026.02
93,471