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

Mathematical Reasoning on MATH500 4-shot

32.2Accuracy

BF16

8.38414.56720.7526.933Apr 12, 2026
Updated 5d ago

Evaluation Results

MethodLinks
2026.04
32.2
2026.04
24.1
2026.04
12.8
2026.04
12.1
2026.04
10.8
2026.04
9.3