Visual Question Answering on V*bench

Metric: Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Hide extra data

Sort:

#	Model↕	Accuracy▼	Extra Data	Paper	Date↕	Code
1	LLaVA-OneVision7B w. FOCUS	92.15	No	-	-	-
2	LLaVA-OneVision7B w. ZoomEye	90.58	No	ZoomEye: Enhancing Multimodal LLMs with Human-Li...	2024-11-25	Code
3	IVM-Enhanced GPT4-V	81.2	No	Instruction-Guided Visual Masking	2024-05-30	Code
4	SEAL	75.39	Yes	V*: Guided Visual Search as a Core Mechanism in ...	2023-12-21	Code
5	LLaVA-OneVision7B	74.46	No	LLaVA-OneVision: Easy Visual Task Transfer	2024-08-06	Code

#1LLaVA-OneVision7B w. FOCUS
92.15
Accuracy
No paper
#2LLaVA-OneVision7B w. ZoomEyeSOTA
90.58
Accuracy· 2024-11-25
ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image Exploration Code
#3IVM-Enhanced GPT4-VSOTA
81.2
Accuracy· 2024-05-30
Instruction-Guided Visual Masking Code
#4SEALSOTA
75.39
Accuracy· Extra Data· 2023-12-21
V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs Code
#5LLaVA-OneVision7B
74.46
Accuracy· 2024-08-06
LLaVA-OneVision: Easy Visual Task Transfer Code