Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Maze Navigation on Maze Navigation (Invalid)
Loading...
4.13
Human Score
sketchVLM
1.0516
1.8508
2.65
3.4492
Apr 23, 2026
Human Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Human Score
sketchVLM
variant=Standard (Squa...
2026.04
4.13
sketchVLM
variant=Star icon variant
2026.04
3.92
Baseline Model (Blue circle)
icon=blue circle
2026.04
3.02
Baseline Model (Multi-colored star)
icon=multi-colored star
2026.04
2.77
Baseline Model (OpenAI icon)
icon=multi-color circl...
2026.04
1.17
Feedback
Search any
task
Search any
task