Spatial Und. (Mono.) on DA-2K (val)
63.54AccuracyQwen2.5-VL-7B + SSL-R1
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen2.5-VL-7B + SSL-R1Model Scale=7B, Training Strategy=+ SSL-R12026.04 | 63.54 | |
| Qwen2.5-VL-3B + SSL-R1Model Scale=3B, Training Strategy=+ SSL-R12026.04 | 61.7 | |
| Qwen2.5-VL-7B + Visual JigsawModel Scale=7B, Training Strategy=+ Visual Jigsaw2026.04 | 59.82 | |
| ThinkLite-VL-7BModel Scale=7B, Training Strategy=Representative Reasoning Model2026.04 | 58.46 | |
| VL-Cogito-7BModel Scale=7B, Training Strategy=Representative Reasoning Model2026.04 | 56.43 | |
| Qwen2.5-VL-3B + Visual JigsawModel Scale=3B, Training Strategy=+ Visual Jigsaw2026.04 | 55.42 | |
| Qwen2.5-VL-7BModel Scale=7B, Training Strategy=Baseline2026.04 | 54.45 | |
| LLaVA-Critic-R1-7BModel Scale=7B, Training Strategy=Representative Reasoning Model2026.04 | 53.82 | |
| Qwen2.5-VL-3BModel Scale=3B, Training Strategy=Baseline2026.04 | 51.89 |