Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
2D discrete grid-world planning on FrozenLake
Loading...
83
Success Rate
AtlasVA
10.2
29.1
48
66.9
May 18, 2026
Success Rate
Updated 15d ago
Evaluation Results
Method
Method
Links
Success Rate
AtlasVA
Model Category=Ours, P...
2026.05
83
o4-mini
Model Category=Proprie...
2026.05
82
Claude Sonnet 4.5
Model Category=Proprie...
2026.05
80
o3
Model Category=Proprie...
2026.05
78
Gemini 2.5 Pro
Model Category=Proprie...
2026.05
78
GPT-5
Model Category=Proprie...
2026.05
77
VAGEN
Model Category=Open-So...
2026.05
71
Claude Sonnet 3.7
Model Category=Proprie...
2026.05
69
Gemini 2.0
Model Category=Proprie...
2026.05
61
Gemini 2.5 flash
Model Category=Proprie...
2026.05
57
GPT-4o
Model Category=Proprie...
2026.05
54
Qwen2.5-VL-72B
Model Category=Open-So...
2026.05
44
Qwen2.5-VL-7B
Model Category=Open-So...
2026.05
14
Qwen2.5-VL-3B
Model Category=Open-So...
2026.05
14
VLM-R1-3B
Model Category=Open-So...
2026.05
13
Feedback
Search any
task
Search any
task