Maze Navigation on MAZENAVIGATION OOD Maze Sizes 7x7 1.0
92EMWan2.2-TI2V-5B (Unseen Visual Icons)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Wan2.2-TI2V-5B (Unseen Visual Icons)Input=Text + Image, Output=Video, Evaluation Protocol=Fine-tuned2026.01 | 92 | 92.6 | |
| Wan2.2-TI2V-5BInput=Text + Image, Output=Video, Evaluation Protocol=Fine-tuned2026.01 | 90 | 92.3 | |
| Qwen3-VL-8B (w/ coordinates)Input=Text + Image, Output=Text, Evaluation Protocol=Fine-tuned2026.01 | 33.2 | 45 | |
| Qwen3-VL-8BInput=Text + Image, Output=Text, Evaluation Protocol=Fine-tuned2026.01 | 20 | 37.3 | |
| VPRL-7B *Input=Image, Output=Image, Evaluation Protocol=Fine-tuned2026.01 | 14 | 25.2 | |
| GPT-5.2Input=Text + Image, Output=Text, Evaluation Protocol=Zero-shot2026.01 | 8.4 | 8.4 | |
| GPT-5.1Input=Text + Image, Output=Text, Evaluation Protocol=Zero-shot2026.01 | 6.32 | 6.72 |