Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal Benchmarking on MMBench (Accuracy, Avg)
Loading...
67.7
Accuracy
LLaVA-1.5
37.02
44.985
52.95
60.915
Jul 2, 2025
Accuracy
Average Score
Updated 16d ago
Evaluation Results
Method
Method
Links
Accuracy
Average Score
LLaVA-1.5
LLM=LLaMA-13B [59], Mo...
2025.07
67.7
64.2
Our Method
LLM=Phi2-2.7B [62], Mo...
2025.07
66.8
62.3
MoE-LLaVA-4Top2
LLM=Phi2-2.7B [62], Mo...
2025.07
65.2
61.1
LLaVA-1.5
LLM=Vicuna-7B [60], Mo...
2025.07
64.3
61.2
Our Method
LLM=StableLM-1.6B [65]...
2025.07
60.6
58.8
MoE-LLaVA-4Top2
LLM=StableLM-1.6B [65]...
2025.07
60.2
57.6
LLaVA-Phi
LLM=Phi2-2.7B [62], Mo...
2025.07
59.8
-
MobileVLM
LLM=MobileLLaMA-2.7B [...
2025.07
59.6
-
IDEFICS
LLM=IDEFICS-65B [58],...
2025.07
54.5
-
Qwen-VL
LLM=Qwen-7B [4], Model...
2025.07
38.2
-
Feedback
Search any
task
Search any
task