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

Multimodal Evaluation on SEED-Bench 2 Plus

71.67Accuracy

Full Prec

-2.27416.92336.1255.317Aug 5, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.08
71.67
2025.08
70.62
2025.08
69.26
2025.08
67.89
2025.08
67.32
2025.08
66.58
2025.08
66.4
2025.08
65.96
2025.08
65.52
2025.08
64.87
2025.08
64.82
2025.08
64.21
2025.08
63.02
2025.08
61.84
2025.08
61.79
2025.08
61.05
2025.08
60.91
2025.08
60.65
2025.08
53.05
2025.08
52.92
2025.08
52.17
2025.08
50.37
2025.08
44.88
2025.08
40.1
2025.08
18.53
2025.08
8.12
2025.08
3.03
2025.08
1.23
2025.08
0.57