Maze Navigation on MAZENAVIGATION 3x3 - 6x6 1.0 (In Distribution)
96EMWan2.2-TI2V-5B
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Wan2.2-TI2V-5BInput=Text + Image, Output=Video, Evaluation Protocol=Fine-tuned2026.01 | 96 | 99 | |
| Wan2.2-TI2V-5B (Unseen Visual Icons)Input=Text + Image, Output=Video, Evaluation Protocol=Fine-tuned2026.01 | 95.5 | 98.2 | |
| VPRL-7B *Input=Image, Output=Image, Evaluation Protocol=Fine-tuned2026.01 | 73.5 | 78.6 | |
| Qwen3-VL-8B (w/ coordinates)Input=Text + Image, Output=Text, Evaluation Protocol=Fine-tuned2026.01 | 72 | 77.3 | |
| Qwen3-VL-8BInput=Text + Image, Output=Text, Evaluation Protocol=Fine-tuned2026.01 | 58.3 | 68.6 | |
| GPT-5.2Input=Text + Image, Output=Text, Evaluation Protocol=Zero-shot2026.01 | 12.5 | 12.5 | |
| GPT-5.1Input=Text + Image, Output=Text, Evaluation Protocol=Zero-shot2026.01 | 10.6 | 10.7 |