Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Hallucination Benchmark on POPE-P
Loading...
87.3
Accuracy
V-STAR
81.58
83.065
84.55
86.035
Apr 11, 2026
Accuracy
Updated 5d ago
Evaluation Results
Method
Method
Links
Accuracy
V-STAR
Data Size=40k
2026.04
87.3
ThinkLite-VL
Data Size=11k
2026.04
86.7
Vision-R1
Data Size=210k
2026.04
85.2
VL-Cogito
Data Size=80k
2026.04
85
R1-Onevision
Data Size=155k
2026.04
84
Qwen2.5VL
2026.04
83.2
OpenVLThinker
Data Size=59.2k
2026.04
82.5
VL-Rethinker
Data Size=39k
2026.04
81.8
Feedback
Search any
task
Search any
task