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

Multidisciplinary knowledge and reasoning on MMMU (dev)

25.33Score

Defender Iter. 3

17.706819.685921.66523.6441Jan 24, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
25.33
2026.01
23.33
2026.01
22.67
2026.01
21.33
2026.01
20.67
2026.01
20.67
2026.01
20
2026.01
19.33
2026.01
18