List your company

Puzzle Solving on Pocket Cube (test)

0.847AccuracyXoT
-0.033880.194810.42350.65219Nov 7, 2023

Evaluation results

MethodLinks
XoTBackbone LLM=GPT-3.5, Revisions (r)=32023.110.8472.01103.22
XoTBackbone LLM=GPT-4, Revisions (r)=32023.110.8361284.63
XoTBackbone LLM=GPT-3.5, Revisions (r)=22023.110.80331.8196.46
XoTBackbone LLM=GPT-4, Revisions (r)=22023.110.79321.79146.52
XoTBackbone LLM=GPT-4, Revisions (r)=12023.110.7761.5475.51
XoTBackbone LLM=GPT-3.5, Revisions (r)=12023.110.74321.5564.63
MCTS2023.110.4644——
ToTBackbone LLM=GPT-4, Search Width (b)=32023.110.195756.58—
GoTBackbone LLM=GPT-4, Top-k (k)=12023.110.18038.55—
ToTBackbone LLM=GPT-3.5, Search Width (b)=32023.110.174958.72—
ToTBackbone LLM=GPT-4, Search Width (b)=12023.110.114816.39—
ToTBackbone LLM=GPT-3.5, Search Width (b)=12023.110.076516.5—
GoTBackbone LLM=GPT-3.5, Top-k (k)=12023.110.01648.93—
IOBackbone LLM=GPT-3.52023.110.01091—
IOBackbone LLM=GPT-42023.110.01091—
CoTBackbone LLM=GPT-42023.110.01091—
CoT-SCBackbone LLM=GPT-42023.110.010910—
CoTBackbone LLM=GPT-3.52023.1101—
CoT-SCBackbone LLM=GPT-3.52023.11010—
LLaMA-2-13B2023.110——