Visual Question Answering on MMBench

Metric: GPT-3.5 score (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	GPT-3.5 score▼	Extra Data	Paper	Date↕	Code
1	LLaVA-InternLM2-ViT + MoSLoRA	73.8	No	Mixture-of-Subspaces in Low-Rank Adaptation	2024-06-16	Code
2	CuMo-7B	73	No	CuMo: Scaling Multimodal LLM with Co-Upcycled Mi...	2024-05-09	Code
3	LLaVA-LLaMA3-8B-ViT + MoSLoRA	73	No	Mixture-of-Subspaces in Low-Rank Adaptation	2024-06-16	Code
4	Video-LaVIT	67.3	No	Video-LaVIT: Unified Video-Language Pre-training...	2024-02-05	Code
5	DreamLLM-7B	49.9	No	DreamLLM: Synergistic Multimodal Comprehension a...	2023-09-20	Code

#1LLaVA-InternLM2-ViT + MoSLoRASOTA
73.8
GPT-3.5 score· 2024-06-16
Mixture-of-Subspaces in Low-Rank Adaptation Code
#2CuMo-7BSOTA
73
GPT-3.5 score· 2024-05-09
CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts Code
#3LLaVA-LLaMA3-8B-ViT + MoSLoRA
73
GPT-3.5 score· 2024-06-16
Mixture-of-Subspaces in Low-Rank Adaptation Code
#4Video-LaVITSOTA
67.3
GPT-3.5 score· 2024-02-05
Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization Code
#5DreamLLM-7BSOTA
49.9
GPT-3.5 score· 2023-09-20
DreamLLM: Synergistic Multimodal Comprehension and Creation Code