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

Mathematical Reasoning on WeMath loose

52.1Accuracy

Qwen2.5-VL-7B

45.96447.55749.1550.743May 12, 2026
Updated 21d ago

Evaluation Results

MethodLinks
2026.05
52.1
2026.05
50.1
2026.05
49.4
2026.05
48.6
2026.05
48.4
2026.05
46.2