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

MME dataset and benchmarks – Page 10 · SOTA2 Research

Research Datasets

MME

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Multimodal Model Evaluation

MME

75Existence Score

3

Discriminative Evaluation

MME

115.88MME Score

3

Adversarial Attack

MME Untargeted v1.0 (test)

48.88GPT-4o Attack Success Rate

3

Adversarial Attack

MME Targeted v1.0 (test)

63.42Success Rate (GPT-4o)

3

General perception and cognition

MME sum

1,695.6Cognition + Perception Sum

3

General Multimodal Question Answering

MME

2,384Total Score

3

Multimodal Evaluation

MME

285.4BD-Metric

3

Multimodal Large Language Model Evaluation

MME (full)

190Existence Score

3

Multi-modal Benchmark

MME

1,509Total Score

3

Multimodal capability profiling

MME Tibetan

88.33Existence Accuracy (Acc)

2

Multimodal Evaluation

MME

1,728Noise Score

2

Multi-modal Model Evaluation

MME

1,807Noise Score

2

Spatial Understanding

MME Position

141MME_Pos Score

2

Paired-prompt evaluation

MME

75.7Simple Accuracy

2

Page 10 of 10

Popular tasks

Multimodal Evaluation Multimodal Understanding Hallucination Evaluation Multimodal Perception Multimodal Model Evaluation

Follow for updates

Join SOTA2 Contact