Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Task#3 on STAR
Loading...
79.5
Accuracy
KGRPO
75.525
77.5125
79.5
81.4875
Oct 22, 2025
Accuracy
CoT Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
CoT Score
KGRPO
Backbone=Qwen2.5-VL-7B...
2025.10
79.5
81.24
Feedback
Search any
task
Search any
task