Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Maze Solving on Wilson maze (test)
Loading...
100
Plan Accuracy
Correct Traces
-2.648
24.001
50.65
77.299
May 19, 2025
Plan Accuracy
Trace Validity
Updated 7d ago
Evaluation Results
Method
Method
Links
Plan Accuracy
Trace Validity
Correct Traces
Backbone=Qwen3-8B-base...
2025.05
100
100
Solution-only
Backbone=Qwen3-8B-base...
2025.05
99.7
0
Swapped Traces
Backbone=Qwen3-8B-base...
2025.05
98
0
Base Model
Backbone=Qwen3-8B-base...
2025.05
1.3
0
Feedback
Search any
task
Search any
task