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

MM STEM & Puzzle on MMMU (dev)

88.2Score

Qwen3-VL-32B

58.87266.48674.181.714Jun 23, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
88.2
2026.06
83.3
2026.06
78.7
2026.06
77.3
2026.06
76.7
2026.06
74.2
2026.06
74
2026.06
70.7
2026.06
70
2026.06
66
2026.06
63.3
2026.06
60