Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

HallusionBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Visual Hallucination EvaluationHallusionBench
Accuracy76.6
156
Hallucination EvaluationHallusionBench
Accuracy82.02
153
Hallucination and Visual Reasoning EvaluationHallusionBench
Accuracy (aACC)81.8
61
Visual ReasoningHallusionBench
Accuracy73.2
43
Multimodal ReasoningHallusionBench
Accuracy0.7293
42
Hallucination AssessmentHallusionBench
Answer Accuracy (aAcc)71.6
39
Multimodal UnderstandingHallusionBench
Accuracy77.2
37
Hallucination RobustnessHallusionBench
Score58.4
37
HallucinationHallusionBench
HallusionBench Score69.2
26
Visual PerceptionHallusionBench
Accuracy71.08
24
Multimodal Hallucination EvaluationHallusionBench
Hallucination Score70.7
22
Hallucination MitigationHallusionBench visual-dependent setting (test)
qAcc (Question Accuracy)33.21
21
Multimodal Hallucination AssessmentHallusionBench
Accuracy70
21
Hallucination DetectionHallusionBench
Hallusion Score67.05
20
General VQAHallusionBench
Accuracy73.48
20
Visual Question AnsweringHallusionBench
Simple Accuracy75.2
19
HallucinationHallusionBench
Pass@174
16
Hallucination DiagnosisHallusionBench
LI Score96
15
PerceptionHallusionBench
Score59.5
15
General visual question answeringHallusionBench
Pass@169.9
14
Hallucination EvaluationHallusionBench 2024
Score52.2
13
Visual Illusion and Hallucination EvaluationHallusionBench (HallB)
HallB Score41.7
13
MM AlignmentHallusionBench
Score67.9
12
Hallucination and Visual Illusion AssessmentHallusionBench
Accuracy22.51
12
Hallucination EvaluationHallusionBench GPT4-assisted (All)
Accuracy (All)49.94
11
Showing 25 of 41 rows