Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multimodal Understanding on LLaVAW
Loading...
75.3
Score
SoM-LLaVA-1.5
36.612
46.656
56.7
66.744
Apr 25, 2024
May 24, 2024
Jun 22, 2024
Jul 21, 2024
Aug 19, 2024
Sep 17, 2024
Oct 17, 2024
Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Score
SoM-LLaVA-1.5
LLM=Vicuna-13B, Res.=3...
2024.04
75.3
SPHINX
LLM=LLAMA2-7B, Res.=224
2024.04
73.5
SoM-LLaVA-1.5-T
LLM=Vicuna-13B, Res.=3...
2024.04
73.3
Arcana
Vision Encoder=VIT-L (...
2024.10
72.7
LLaVA-1.5
LLM=Vicuna-13B, Res.=3...
2024.04
70.7
Arcana
Vision Encoder=VIT-L (...
2024.10
67.3
LLaVA-v1.5
Vision Encoder=VIT-L (...
2024.10
63.4
LLaVA
Vision Encoder=VIT-L (...
2024.10
63
InstructBLIP
Vision Encoder=ViT-g (...
2024.10
60.9
InstructBLIP
LLM=Vicuna-7B, Res.=22...
2024.04
60.9
InstructBLIP
LLM=Vicuna-13B, Res.=2...
2024.04
58.2
MiniGPT-4
Vision Encoder=ViT-g (...
2024.10
45.1
BLIP-2
LLM=Vicuna-13B, Res.=2...
2024.04
38.1
Feedback
Search any
task
Search any
task