Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Dynamic Spatial Reasoning on SAT Synthetic
Loading...
65.2
Accuracy
World2VLM-GRPO
38.576
45.488
52.4
59.312
Apr 29, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
World2VLM-GRPO
Setting=HY-WorldPlay a...
2026.04
65.2
World2VLM-GRPO
Setting=SVC as WM
2026.04
59.2
World2VLM-SFT
Setting=HY-WorldPlay a...
2026.04
57.2
Qwen2.5-VL-7B + WM
Setting=MindJourney-st...
2026.04
51.75
World2VLM-SFT
Setting=SVC as WM
2026.04
50
Qwen2.5-VL-7B
Setting=Base VLM
2026.04
39.6
Feedback
Search any
task
Search any
task