Visual Question Answering (VQA) on AutoHallusion

Metric: Overall Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	Overall Accuracy▼	Extra Data	Paper	Date↕	Code
1	GPT-4V	66	No	AutoHallusion: Automatic Generation of Hallucina...	2024-06-16	Code
2	Gemini Pro Vision	51.4	No	-	-	-
3	miniGPT4	51	No	MiniGPT-4: Enhancing Vision-Language Understandi...	2023-04-20	Code
4	LLaVA-1.5	44.5	No	Improved Baselines with Visual Instruction Tuning	2023-10-05	Code
5	Claude 3	37.1	No	-	-	-

#1GPT-4VSOTA
66
Overall Accuracy· 2024-06-16
AutoHallusion: Automatic Generation of Hallucination Benchmarks for Vision-Language Models Code
#2Gemini Pro Vision
51.4
Overall Accuracy
No paper
#3miniGPT4SOTA
51
Overall Accuracy· 2023-04-20
MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models Code
#4LLaVA-1.5
44.5
Overall Accuracy· 2023-10-05
Improved Baselines with Visual Instruction Tuning Code
#5Claude 3
37.1
Overall Accuracy
No paper