Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Pocket Cube solving on Pocket Cube (test)
Loading...
77.41
Multi Accuracy
XoT (w/ 1 r)
-2.9092
17.9429
38.795
59.6471
Nov 7, 2023
Multi Accuracy
Solution Count
Updated 3d ago
Evaluation Results
Method
Method
Links
Multi Accuracy
Solution Count
XoT (w/ 1 r)
LLM=GPT-4, LLM invoked...
2023.11
77.41
1.72
XoT (w/ 1 r)
LLM=GPT-3.5, LLM invok...
2023.11
48.72
2.2
GoT (k=3)
LLM=GPT-4, LLM invoked...
2023.11
16.85
2.77
ToT (b=3)
LLM=GPT-4, LLM invoked...
2023.11
6.52
2.99
ToT (b=3)
LLM=GPT-3.5, LLM invok...
2023.11
5.83
2.99
IO
LLM=GPT-4, LLM invoked...
2023.11
1.09
1.98
GoT (k=3)
LLM=GPT-3.5, LLM invok...
2023.11
1.09
2.99
CoT
LLM=GPT-4, LLM invoked...
2023.11
0.82
1.91
CoT-SC
LLM=GPT-4, LLM invoked...
2023.11
0.82
2.92
CoT
LLM=GPT-3.5, LLM invok...
2023.11
0.55
1.05
IO
LLM=GPT-3.5, LLM invok...
2023.11
0.27
2
CoT-SC
LLM=GPT-3.5, LLM invok...
2023.11
0.18
2.9
Feedback
Search any
task
Search any
task