Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Game of 24 on Game of 24 100 tasks GPT-4
Loading...
74
Success Rate
ToT
1.2
20.1
39
57.9
May 17, 2023
Success Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Success Rate
ToT
Breadth (b)=5
2023.05
74
CoT (best of 100)
Sample size (k)=100, S...
2023.05
49
ToT
Breadth (b)=1
2023.05
45
IO (best of 100)
Sample size (k)=100, S...
2023.05
33
IO + Refine
Sample size (k)=10, St...
2023.05
27
CoT-SC
Prompting strategy=Cha...
2023.05
9
IO prompt
Prompting strategy=Inp...
2023.05
7.3
CoT prompt
Prompting strategy=Cha...
2023.05
4
Feedback
Search any
task
Search any
task