Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal Understanding on SEED-Bench-I Image Subset
Loading...
71
Accuracy
Mutual
69.96
70.23
70.5
70.77
May 28, 2026
Accuracy
Average Performance
Updated 5d ago
Evaluation Results
Method
Method
Links
Accuracy
Average Performance
Mutual
Average Token Budget=1...
2026.05
71
99.4
VisionZip ‡
Average Token Budget=6...
2026.05
71
95.1
CLS
Average Token Budget=1...
2026.05
70.8
99.3
Vanilla
Average Token Budget=5...
2026.05
70.7
100
VisionZip
Average Token Budget=1...
2026.05
70.7
98.2
VisionZip
Average Token Budget=6...
2026.05
70.7
91.8
Mutual
Average Token Budget=1...
2026.05
70.6
98.4
Mutual
Average Token Budget=6...
2026.05
70.6
96.8
CLS
Average Token Budget=6...
2026.05
70.5
96.6
CLS
Average Token Budget=1...
2026.05
70.3
98.6
VisionZip ‡
Average Token Budget=1...
2026.05
70.2
98.4
VisionZip ‡
Average Token Budget=1...
2026.05
70.1
97
VisionZip
Average Token Budget=1...
2026.05
70
96.1
Feedback
Search any
task
Search any
task