Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Large Vision-Language Model Evaluation on LLAVA (bench)
Loading...
77.8
Score
CogVLM-Chat
22.888
37.144
51.4
65.656
Nov 6, 2023
Score
Updated 3d ago
Evaluation Results
Method
Method
Links
Score
CogVLM-Chat
LLM=Vicuna-7B
2023.11
77.8
LLaVA-1.5
LLM=Vicuna-13B
2023.11
64.6
LLaVA-1.5
LLM=Vicuna-7B
2023.11
60.7
InstructBLIP
LLM=Vicuna-7B
2023.11
59.8
IDEFICS-Instruct
LLM=LLaMA-65B
2023.11
56.9
Emu2-Chat
LLM=LLaMA-33B
2023.11
56.4
MiniGPT-4
LLM=Vicuna-7B
2023.11
45.1
OpenFlamingo
LLM=MPT-7B
2023.11
34.2
Fuyu
LLM=Fuyu-8B
2023.11
27.4
mPLUG-Owl2
LLM=LLaMA2-7B
2023.11
25
Feedback
Search any
task
Search any
task