Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Visual Perception on Hallusion
Loading...
72.45
Accuracy
Qwen2.5-VL-32B-Instruct + NoisyRollout
60.3652
63.5026
66.64
69.7774
Mar 11, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen2.5-VL-32B-Instruct + NoisyRollout
Student Model=Qwen2.5-...
2026.03
72.45
NoisyRollout
Teacher Model=Qwen2.5-...
2026.03
70.66
REOPOLD
Teacher Model=Qwen2.5-...
2026.03
70.14
GRPO
Teacher Model=Qwen2.5-...
2026.03
69.8
RKL
Teacher Model=Qwen2.5-...
2026.03
69.51
Qwen2.5-VL-7B-Instruct
Student Model=Qwen2.5-...
2026.03
65.62
REOPOLD
Teacher Model=Qwen2.5-...
2026.03
63.62
PAPO
Teacher Model=Qwen2.5-...
2026.03
61.62
Qwen2.5-VL-3B-Instruct
Student Model=Qwen2.5-...
2026.03
61.51
RKL
Teacher Model=Qwen2.5-...
2026.03
60.83
Feedback
Search any
task
Search any
task