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

Vision-language model merging on MM-MergeBench seen tasks

69.23Average Absolute Accuracy

Individual

42.335649.317856.363.2822Mar 6, 2026
Updated 4mo ago

Evaluation Results

MethodLinks
2026.03
69.23
2026.03
63.62
2026.03
59.63
2026.03
57.33
2026.03
53.93
2026.03
53.84
2026.03
53.7
2026.03
53.09
2026.03
43.37