Visual Question Answering (VQA) on VLM2-Bench

Metric: GC-mat (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	GC-mat▼	Extra Data	Paper	Date↕	Code
1	GPT-4o	37.45	No	GPT-4o System Card	2024-10-25	-
2	Qwen2.5-VL-7B	35.91	No	Qwen2.5-VL Technical Report	2025-02-19	Code
3	InternVL2.5-26B	30.5	No	Expanding Performance Boundaries of Open-Source ...	2024-12-06	Code
4	Qwen2-VL-7B	27.8	No	Qwen2-VL: Enhancing Vision-Language Model's Perc...	2024-09-18	Code
5	InternVL2.5-8B	21.24	No	Expanding Performance Boundaries of Open-Source ...	2024-12-06	Code
6	LLaVA-Video-7B	18.53	No	Video Instruction Tuning With Synthetic Data	2024-10-03	-
7	mPLUG-Owl3-7B	17.37	No	mPLUG-Owl3: Towards Long Image-Sequence Understa...	2024-08-09	Code
8	LLaVA-OneVision-7B	16.6	No	LLaVA-OneVision: Easy Visual Task Transfer	2024-08-06	Code
9	LongVA-7B	14.29	No	Long Context Transfer from Language to Vision	2024-06-24	Code

#1GPT-4oSOTA
37.45
GC-mat· 2024-10-25
GPT-4o System Card
#2Qwen2.5-VL-7B
35.91
GC-mat· 2025-02-19
Qwen2.5-VL Technical Report Code
#3InternVL2.5-26B
30.5
GC-mat· 2024-12-06
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling Code
#4Qwen2-VL-7BSOTA
27.8
GC-mat· 2024-09-18
Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution Code
#5InternVL2.5-8B
21.24
GC-mat· 2024-12-06
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling Code
#6LLaVA-Video-7B
18.53
GC-mat· 2024-10-03
Video Instruction Tuning With Synthetic Data
#7mPLUG-Owl3-7BSOTA
17.37
GC-mat· 2024-08-09
mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models Code
#8LLaVA-OneVision-7BSOTA
16.6
GC-mat· 2024-08-06
LLaVA-OneVision: Easy Visual Task Transfer Code
#9LongVA-7BSOTA
14.29
GC-mat· 2024-06-24
Long Context Transfer from Language to Vision Code