List your company

Multi-Solution Arithmetic Reasoning on Game of 24 (4nu 137 test)

76.25Multi Solution AccuracyXoT
-1.781218.476938.73558.9931Nov 7, 2023

Evaluation results

MethodLinks
XoTLLM Backbone=GPT-4, Number of thought revisions (r)=12023.1176.252.362.31109.64
XoTLLM Backbone=GPT-3.5, Number of thought revisions (r)=12023.1162.92.293.51116.34
ToTLLM Backbone=GPT-4, Branching factor (b)=32023.1139.92.7839.83—
GoTLLM Backbone=GPT-4, k-value (k)=32023.1110.461.397—
IOLLM Backbone=GPT-42023.118.272.991—
GoTLLM Backbone=GPT-3.5, k-value (k)=32023.118.031.937—
CoT-SCLLM Backbone=GPT-42023.118.032.9910—
CoTLLM Backbone=GPT-42023.117.792.941—
IOLLM Backbone=GPT-3.52023.114.872.881—
ToTLLM Backbone=GPT-3.5, Branching factor (b)=32023.113.412.9943.96—
CoT-SCLLM Backbone=GPT-3.52023.111.72.7610—
CoTLLM Backbone=GPT-3.52023.111.222.771—