List your company

Visual Question Answering on PuzzleVQA

61AccuracyOctoTools
51.84854.22456.658.976Feb 16, 2025

Evaluation results

MethodLinks
OctoToolsBackbone=gpt-4o-2024-08-06, Modality=Vision, Domain=General, Visual Understanding=true, Numerical Calculation=false, Knowledge Retrieval=false, Multi-step Reasoning=true2025.02618.87
OctoToolsbaseBackbone=gpt-4o-2024-08-06, Modality=Vision, Domain=General, Visual Understanding=true, Numerical Calculation=false, Knowledge Retrieval=false, Multi-step Reasoning=true2025.0259.3——
CoTBackbone=gpt-4o-2024-08-06, Modality=Vision, Domain=General, Visual Understanding=true, Numerical Calculation=false, Knowledge Retrieval=false, Multi-step Reasoning=true2025.0254——
0-shotBackbone=gpt-4o-2024-08-06, Modality=Vision, Domain=General, Visual Understanding=true, Numerical Calculation=false, Knowledge Retrieval=false, Multi-step Reasoning=true2025.0252.2——