List your company

Visual Hallucination Detection on Hallusion-VD

63.3AccuracyOctoTools
51.54854.59957.6560.701Feb 16, 2025

Evaluation results

MethodLinks
OctoToolsBackbone=gpt-4o-2024-08-06, Modality=Vision, Domain=General, Visual Understanding=true, Numerical Calculation=false, Knowledge Retrieval=true, Multi-step Reasoning=false2025.0263.311.310
OctoToolsbaseBackbone=gpt-4o-2024-08-06, Modality=Vision, Domain=General, Visual Understanding=true, Numerical Calculation=false, Knowledge Retrieval=true, Multi-step Reasoning=false2025.0259——
CoTBackbone=gpt-4o-2024-08-06, Modality=Vision, Domain=General, Visual Understanding=true, Numerical Calculation=false, Knowledge Retrieval=true, Multi-step Reasoning=false2025.0253.3——
0-shotBackbone=gpt-4o-2024-08-06, Modality=Vision, Domain=General, Visual Understanding=true, Numerical Calculation=false, Knowledge Retrieval=true, Multi-step Reasoning=false2025.0252——