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

Multimodal Mathematical Reasoning on DynaMath-W

60.5Accuracy

Seed-1.5-thinking

19.62830.23940.8551.461Dec 19, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.12
60.5
2025.12
57.1
2025.12
48.3
2025.12
46.9
2025.12
30.3
2025.12
27.5
2025.12
27.4
2025.12
27.2
2025.12
25.2
2025.12
24
2025.12
22.4
2025.12
22
2025.12
21.2
2025.12
21.2