Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Prior-Sensitive Evaluation on ViLP-P pure-question
Loading...
69.5
Score
ViGOS
35.7
44.475
53.25
62.025
Jun 17, 2026
Score
Prior Utilization
Updated 1mo ago
Evaluation Results
Method
Method
Links
Score
Prior Utilization
ViGOS
Backbone=Qwen2.5-VL 3B
2026.06
69.5
90
OPSD
Backbone=Qwen2.5-VL 3B
2026.06
66.83
92
Visionary-R1-3B
Method Category=RL Met...
2026.06
65.17
88
ViGOS
Backbone=Qwen2.5-VL 7B
2026.06
61.67
91.67
Vision-R1-7B
Method Category=RL Met...
2026.06
57.83
90
OPSD
Backbone=Qwen2.5-VL 7B
2026.06
57
91.67
Baseline
Backbone=Qwen2.5-VL 3B
2026.06
55.67
80.67
Baseline
Backbone=Qwen2.5-VL 7B
2026.06
37
58.67
Feedback
Search any
task
Search any
task