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

LLaVA-NeXT dataset and benchmarks · SOTA2 Research

Research Datasets

LLaVA-NeXT

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Multimodal Understanding and Question Answering

LLaVA-NeXT Evaluation Suite (GQA, SQA-IMG, VQA-Text, POPE, MME, MMB-EN, MMB-CN, MMVet) 13B (test)

64.4GQA Score

28

Multimodal Question Answering

LLaVA-NeXT-7B Evaluation Suite

5.6FLOPs (TFLOPs)

6

Layer Pruning Efficiency Evaluation

LLaVA-NeXT 8B

18.1Peak VRAM (GB)

6

Multimodal Understanding

LLaVA-NeXT Evaluation Suite

100Average Accuracy

6

Textual Concept Interpretability

LLaVA-NeXT textual concepts

81Detection Score

3

Popular tasks

Multimodal Understanding Multimodal Question Answering Multimodal Understanding and Question Answering Layer Pruning Efficiency Evaluation Textual Concept Interpretability

Follow for updates

Join SOTA2 Contact