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

Large Vision-Language Model Evaluation on DRBench B

27.04MCQ Score

SCI7

-1.08166.219213.5220.8208Mar 8, 2026
Updated 2mo ago

Evaluation Results

MethodLinks
2026.03
27.0429.6627.65
2026.03
24.9125.6925.09
2026.03
24.8638.2627.01
2026.03
23.8137.9726.08
2026.03
21.6726.322.74
2026.03
21.2235.3623.48
2026.03
19.8121.7120.26
2026.03
16.9125.2218.24
2026.03
16.216.8216.35
2026.03
15.7421.7117.13
2026.03
12.9823.4814.66
2026.03
12.6525.5114.71
2026.03
5.378.566.11
2026.03
000