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

Large Vision-Language Model Evaluation on DRBench S Subset

47.22MCQ Accuracy

M3ID

37.735240.197642.6645.1224Mar 8, 2026
Updated 2mo ago

Evaluation Results

MethodLinks
2026.03
47.2241.1643.87
2026.03
47.2242.4444.58
2026.03
47.2245.9846.54
2026.03
46.8340.8443.52
2026.03
45.6336.6640.67
2026.03
44.0542.4443.16
2026.03
40.660.6547.95
2026.03
40.556.5346.38
2026.03
40.160.6547.64
2026.03
39.956.3645.94
2026.03
39.660.3147.2
2026.03
39.237.6338.63
2026.03
3957.5645.81
2026.03
38.134.4136.06