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

Mathematical Reasoning on LMB (LiveMathBench)

35.8Accuracy

RePro

6.36814.00921.6529.291Dec 1, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.12
35.8
2025.12
35.3
2025.12
35.1
2025.12
22
2025.12
20.5
2025.12
20.5
2025.12
19.5
2025.12
19.5
2025.12
18.8
2025.12
18.8
2025.12
18.8
2025.12
18.5
2025.12
17.8
2025.12
17.5
2025.12
17.5
2025.12
16
2025.12
15.8
2025.12
15
2025.12
14.5
2025.12
14.5
2025.12
12.5
2025.12
10.5
2025.12
7.5