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

Cloze Task on MLLMU-Bench (test)

13.04Accuracy

GA_Diff

1.64164.60087.5610.5192May 26, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.05
13.04
2026.05
13.04
2026.05
13.04
2026.05
13.04
2026.05
13.04
2026.05
13.04
2026.05
13.03
2026.05
10.87
2026.05
10.87
2026.05
10.87
2026.05
10.87
2026.05
10.87
2026.05
10.86
2026.05
10.86
2026.05
8.69
2026.05
8.69
2026.05
8.69
2026.05
8.34
2026.05
4.17
2026.05
4.17
2026.05
2.18
2026.05
2.17
2026.05
2.08
2026.05
2.08
2026.05
2.08
2026.05
2.08
2026.05
2.08
2026.05
2.08
2026.05
2.08
2026.05
2.08