Task#5 on STAR
82.66ScoreQwen3-VL-8B S2(KGRPO)
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3-VL-8B S2(KGRPO)Backbone=Qwen3-VL-8B, Setting=S2(KGRPO)2025.10 | 82.66 | |
| GPT-4oBackbone=GPT-4o2025.10 | 82.38 | |
| Qwen3-VL-4B S2(KGRPO)Backbone=Qwen3-VL-4B, Setting=S2(KGRPO)2025.10 | 81.82 | |
| Qwen3-VL-2B S2(KGRPO)Backbone=Qwen3-VL-2B, Setting=S2(KGRPO)2025.10 | 80.36 | |
| KGRPOBackbone=Qwen2.5-VL-7B, Settings=S22025.10 | 77.19 | |
| Qwen2.5-VL-7B S2(KGRPO)Backbone=Qwen2.5-VL-7B, Setting=S2(KGRPO)2025.10 | 77.19 | |
| Qwen2.5-VL-32B S2(SimPO)Backbone=Qwen2.5-VL-32B, Setting=S2(SimPO)2025.10 | 74.16 | |
| Qwen2.5-VL-3B S2(KGRPO)Backbone=Qwen2.5-VL-3B, Setting=S2(KGRPO)2025.10 | 71.51 | |
| GPT-4o-miniBackbone=GPT-4o-mini2025.10 | 69.13 | |
| GPT-4vBackbone=GPT-4v2025.10 | 59.25 | |
| GPT-4oBackbone=GPT-4o2025.10 | 57.63 | |
| QVQ-72BBackbone=QVQ-72B2025.10 | 50.13 |