Fine-Grained Perception & Understanding on V* (test)
82.2AccuracyQwen2.5-VL-7B + Visual Jigsaw
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen2.5-VL-7B + Visual JigsawModel Scale=7B, Training Strategy=+ Visual Jigsaw2026.04 | 82.2 | |
| Qwen2.5-VL-7B + SSL-R1Model Scale=7B, Training Strategy=+ SSL-R12026.04 | 81.68 | |
| Qwen2.5-VL-3B + SSL-R1Model Scale=3B, Training Strategy=+ SSL-R12026.04 | 80.63 | |
| VL-Cogito-7BModel Scale=7B, Training Strategy=Representative Reasoning Model2026.04 | 79.58 | |
| Qwen2.5-VL-3B + Visual JigsawModel Scale=3B, Training Strategy=+ Visual Jigsaw2026.04 | 78.53 | |
| LLaVA-Critic-R1-7BModel Scale=7B, Training Strategy=Representative Reasoning Model2026.04 | 78.01 | |
| ThinkLite-VL-7BModel Scale=7B, Training Strategy=Representative Reasoning Model2026.04 | 76.96 | |
| Qwen2.5-VL-7BModel Scale=7B, Training Strategy=Baseline2026.04 | 76.96 | |
| Qwen2.5-VL-3BModel Scale=3B, Training Strategy=Baseline2026.04 | 76.44 |