Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

MMHal-Bench dataset and benchmarks · SOTA2 Research

Research Datasets

MMHal-Bench

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Hallucination Evaluation

MMHal-Bench

84.2MMHal Score

309

Multimodal Hallucination Evaluation

MMHal-Bench

46Average Score

140

Image+Text-to-Text Hallucination Evaluation

MMHal-Bench

79BERT Score

18

Vision-Language Hallucination

MMHal-Bench

32Hal

13

Generative Hallucination Mitigation

MMHal-Bench

3.49Overall Score

13

Multi-modal Hallucination Evaluation

MMHal-Bench v1.0 (test)

2.14Overall Score

12

Hallucination Evaluation

MMHal-Bench-V

2.57Hallucination Score

9

Multi-modal Hallucination Evaluation

MMHal-Bench

1.83Attribute Failure Score

5

Popular tasks

Hallucination Evaluation Multi-modal Hallucination Evaluation Multimodal Hallucination Evaluation Generative Hallucination Mitigation Image+Text-to-Text Hallucination Evaluation

Follow for updates

Join SOTA2 Contact