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

Mathematical Reasoning on MATH original and paraphrased (train)

35.29Reference Score/Rate

Qwen-Math

-1.21928.2591517.737527.21585May 21, 2026
Updated 12d ago

Evaluation Results

MethodLinks
2026.05
35.2953.14---1
2026.05
35.2947.14---1
2026.05
33.86-50.43--1
2026.05
33.86-46--1
2026.05
20.7137.14---1
2026.05
20.7130---1
2026.05
18.57-31--1
2026.05
18.57-26.57--0.999
2026.05
0.305--42.7-0.998
2026.05
0.305--40-0.998
2026.05
0.277---42.60.998
2026.05
0.277---38.80.998
2026.05
0.251--40.3-0.998
2026.05
0.251--32.7-0.998
2026.05
0.185---34.70.998
2026.05
0.185---28.40.998