Video Question Answering on Zero-shot Video Question Answering on LongVideoBench

Metric: Accuracy (% ) (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Hide extra data

Sort:

#	Model↕	Accuracy (% )▼	Extra Data	Paper	Date↕	Code
1	Gemini 1.5 Pro	66.7	Yes	Gemini 1.5: Unlocking multimodal understanding a...	2024-03-08	Code
2	Video-RAG (based on LLaVA-Video)	65.4	Yes	Video-RAG: Visually-aligned Retrieval-Augmented ...	2024-11-20	Code
3	GPT-4o	64	Yes	GPT-4o: Visual perception performance of multimo...	2024-06-14	-
4	LLaVA-Video	61.9	Yes	Video Instruction Tuning With Synthetic Data	2024-10-03	-

#1Gemini 1.5 ProSOTA
66.7
Accuracy (% )· Extra Data· 2024-03-08
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context Code
#2Video-RAG (based on LLaVA-Video)
65.4
Accuracy (% )· Extra Data· 2024-11-20
Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension Code
#3GPT-4o
64
Accuracy (% )· Extra Data· 2024-06-14
GPT-4o: Visual perception performance of multimodal large language models in piglet activity understanding
#4LLaVA-Video
61.9
Accuracy (% )· Extra Data· 2024-10-03
Video Instruction Tuning With Synthetic Data