Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multi-modal Reasoning and Understanding on MM-Vet
Loading...
53.4
Accuracy
InstructBLIP
28.96
35.305
41.65
47.995
Jun 6, 2024
Accuracy
Updated 3d ago
Evaluation Results
Method
Method
Links
Accuracy
InstructBLIP
LLM=Vicuna-7B, Eff. Re...
2024.06
53.4
LLaVA-Next
LLM=Vicuna-13B, Eff. R...
2024.06
49.1
LLaVA-Next
LLM=Vicuna-7B, Eff. Re...
2024.06
44.1
DeepStack-L-HD
LLM=Vicuna-13B, Eff. R...
2024.06
39.3
VILA
LLM=Llama2-13B, Eff. R...
2024.06
38.8
DeepStack-L-HD
LLM=Vicuna-7B, Eff. Re...
2024.06
37.5
DeepStack-L
LLM=Vicuna-13B, Eff. R...
2024.06
35.9
LLaVA-1.5
LLM=Vicuna-13B, Eff. R...
2024.06
35.4
VILA
LLM=Llama2-7B, Eff. Re...
2024.06
34.9
DeepStack-V
LLM=Vicuna-7B, Eff. Re...
2024.06
33
DeepStack-V
LLM=Vicuna-13B, Eff. R...
2024.06
31.1
DeepStack-L
LLM=Vicuna-7B, Eff. Re...
2024.06
29.9
Feedback
Search any
task
Search any
task