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

Large Multi-modal Model Evaluation research benchmarks · SOTA2 Research

Large Multi-modal Model Evaluation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

1,514.46Perception Score

22

Apr 8, 2026

LLaVA-Bench Tool Use (test)

0.893Grounding

8

Feb 26, 2026

LLaVA-Bench In-the-Wild v1

65.5Conversational Score

6

Feb 26, 2026

LLaVA-Bench COCO v1

0.82Conv Score

6

Feb 26, 2026

Popular datasets

LLaVA-Bench MME

Follow for updates

Join SOTA2 Contact