Tangram puzzle solving (Translation) on TANGRAMPUZZLE (Unseen)
76Strict GCQwen-Image-Edit-20B
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Qwen-Image-Edit-20BInput=Text + Image, Output=Image2026.01 | 76 | 0.954 | 0.997 | |
| Wan2.2-TI2V-5BInput=Text + Image, Output=Video2026.01 | 60.8 | 0.92 | 0.97 | |
| Nano BananaInput=Text + Image, Output=Image2026.01 | 3.9 | 0.513 | 0.745 | |
| Qwen3-VL-8BInput=Text + Image, Output=Image2026.01 | 1.6 | 0.589 | 0.824 |