Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Spatial Planning on Sokoban
Loading...
79
Success Rate
AtlasVA
9.84
27.795
45.75
63.705
May 14, 2026
May 15, 2026
May 16, 2026
May 17, 2026
May 18, 2026
Success Rate
Updated 15d ago
Evaluation Results
Method
Method
Links
Success Rate
AtlasVA
Model Category=Ours, P...
2026.05
79
GPT-5
Model Category=Proprie...
2026.05
70
VAGEN
Model Category=Open-So...
2026.05
61
o3
Model Category=Proprie...
2026.05
60
Gemini 2.5 Pro
Model Category=Proprie...
2026.05
58
Gemini 2.5 flash
Model Category=Proprie...
2026.05
52
o4-mini
Model Category=Proprie...
2026.05
44
GPT-4o
Model Category=Proprie...
2026.05
43
ActFocus
Backbone=3B, Evaluatio...
2026.05
37.5
ActFocus
Backbone=0.5B, Evaluat...
2026.05
34
Claude Sonnet 4.5
Model Category=Proprie...
2026.05
31
Gemini 2.0
Model Category=Proprie...
2026.05
28
Uniform
Backbone=3B, Evaluatio...
2026.05
26.2
Claude Sonnet 3.7
Model Category=Proprie...
2026.05
25
Qwen2.5-VL-72B
Model Category=Open-So...
2026.05
18
Qwen2.5-VL-3B
Model Category=Open-So...
2026.05
14
Qwen2.5-VL-7B
Model Category=Open-So...
2026.05
13
VLM-R1-3B
Model Category=Open-So...
2026.05
13
Uniform
Backbone=0.5B, Evaluat...
2026.05
12.5
Feedback
Search any
task
Search any
task