List your company

Visual Reasoning on Geometric Shapes

95.2AccuracyRoT
48.460.5572.784.85Oct 3, 2023Dec 5, 2023Feb 6, 2024Apr 9, 2024Jun 11, 2024Aug 13, 2024Oct 16, 2024

Evaluation results

MethodLinks
RoTBackbone=GPT-4, Shots=2-shot2024.1095.2
RoTBackbone=GPT-4, Shots=1-shot2024.1094.8
BOTBackbone=GPT-4, Shots=2-shot2024.1090.7
BOTBackbone=GPT-4, Shots=1-shot2024.1090.4
RoTBackbone=GPT-3.5-turbo, Shots=2-shot2024.1088.7
RoTBackbone=GPT-3.5-turbo, Shots=1-shot2024.1088.4
BOTBackbone=GPT-3.5-turbo, Shots=2-shot2024.1084.3
BOTBackbone=GPT-3.5-turbo, Shots=1-shot2024.1083.1
Meta-promptingBackbone=GPT-4, Shots=2-shot2024.1078.2
Meta-promptingBackbone=GPT-4, Shots=1-shot2024.1076.7
Meta-promptingBackbone=GPT-3.5-turbo, Shots=2-shot2024.1071
Meta-promptingBackbone=GPT-3.5-turbo, Shots=1-shot2024.1069.5
COTBackbone=GPT-4, Shots=2-shot2024.1060.9
TOTBackbone=GPT-4, Shots=2-shot2024.1060.1
GOTBackbone=GPT-3.5-turbo, Shots=2-shot2024.1058.9
GOTBackbone=GPT-3.5-turbo, Shots=1-shot2024.1058.6
TOTBackbone=GPT-4, Shots=1-shot2024.1058.6
TOTBackbone=GPT-3.5-turbo, Shots=2-shot2024.1058.5
GOTBackbone=GPT-4, Shots=2-shot2024.1057.7
COTBackbone=GPT-4, Shots=1-shot2024.1057.4
TOTBackbone=GPT-3.5-turbo, Shots=1-shot2024.1056.2
GOTBackbone=GPT-4, Shots=1-shot2024.1056.2
PROMPTEDPrompting Technique=PROMPTED2023.1055.2
Zero-ShotPrompting Technique=Zero-Shot2023.1054.4
Zero-Shot CoTPrompting Technique=Zero-Shot Chain-of-Thought2023.1054.4
COTBackbone=GPT-3.5-turbo, Shots=2-shot2024.1053.2
Output RefinementPrompting Technique=Output Refinement2023.1052.8
COTBackbone=GPT-3.5-turbo, Shots=1-shot2024.1050.2