Prior-Sensitive Evaluation on ViLP-F with-fact
70.17ScoreViGOS
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ViGOSBackbone=Qwen2.5-VL 3B2026.06 | 70.17 | 97.67 | |
| OPSDBackbone=Qwen2.5-VL 3B2026.06 | 67.17 | 97.33 | |
| Visionary-R1-3BMethod Category=RL Methods, Backbone Size=3B2026.06 | 64.67 | 94.67 | |
| ViGOSBackbone=Qwen2.5-VL 7B2026.06 | 62.67 | 97 | |
| BaselineBackbone=Qwen2.5-VL 3B2026.06 | 59.5 | 93.33 | |
| OPSDBackbone=Qwen2.5-VL 7B2026.06 | 58 | 97.67 | |
| Vision-R1-7BMethod Category=RL Methods, Backbone Size=7B2026.06 | 57.17 | 95.67 | |
| BaselineBackbone=Qwen2.5-VL 7B2026.06 | 42 | 73.33 |