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

Mathematical Reasoning on HMMT (Pass@1 Accuracy)

32.35Pass@1 Accuracy

Base model

5.642812.576419.5126.4436Jun 11, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
32.35
2026.06
16.67
2026.06
16.67
2026.06
16.67
2026.06
13.33
2026.06
13.33
2026.06
13.33
2026.06
13.33
2026.06
13.33
2026.06
6.67