Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Language Shortcut Robustness on ViLP
Loading...
59.3
Accuracy
Vision-SR1
44.532
48.366
52.2
56.034
Aug 27, 2025
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Vision-SR1
Backbone=Mimo-VL-7B
2025.08
59.3
Vision-R1
Backbone=Mimo-VL-7B
2025.08
58.2
before RL
Backbone=Mimo-VL-7B
2025.08
56.4
Vision-SR1
Backbone=Qwen2.5-VL-7B
2025.08
52.6
Vision-R1
Backbone=Qwen2.5-VL-7B
2025.08
51.3
before RL
Backbone=Qwen2.5-VL-7B
2025.08
45.1
Feedback
Search any
task
Search any
task