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

Math Reasoning on AMC (Avg@32, Pass@16)

73.64Avg@32

training-time reweighting

25.838.2250.6463.06Mar 23, 2026
Updated 25d ago

Evaluation Results

MethodLinks
2026.03
73.6489.69
2026.03
73.0489.03
2026.03
71.0592.3
2026.03
69.1388.51
2026.03
40.6279.25
2026.03
27.6478.09