List your company
ResearchFormerly WizWand

Multimodal Reasoning on LLaVA-Bench Wild

74.5GPT-4 ScoreLLaVA-1.5 + MMInstruct
-2.179217.727937.63557.5421Mar 27, 2024Apr 15, 2024May 5, 2024May 24, 2024Jun 13, 2024Jul 2, 2024Jul 22, 2024
Updated 8mo ago

Evaluation results

MethodLinks
LLaVA-1.5 + MMInstructLLM=Vicuna-13B2024.0774.5
LLaVA-1.5 + MMInstructLLM=Vicuna-7B2024.0771
LLaVA-1.5LLM=Vicuna-13B2024.0770.7
LLaVA-1.5LLM=Vicuna-7B2024.0763.4
InstructBLIPLLM=Vicuna-7B2024.0760.9
InstructBLIPLLM=Vicuna-13B2024.0758.2
BLIP-2LLM=Vicuna-13B2024.0738.1
LLaVA-VTLLM=V-13B, #PT=558K, #IT=665K, Representation=E + T2024.030.891
LLaVA-CapLLM=V-13B, #PT=558K, #IT=665K, Representation=E + T2024.030.889
LLaVA-SGLLM=V-13B, #PT=558K, #IT=665K, Representation=E + T2024.030.868
LLaVA-1.5LLM=V-13B, #PT=558K, #IT=665K, Representation=Visual Embeddings (E)2024.030.867
LLaVA-DCapLLM=V-13B, #PT=558K, #IT=665K, Representation=E + T2024.030.864
LLaVA-VTLLM=V-7B, #PT=558K, #IT=665K, Representation=E + T2024.030.85
Vicuna-VTLLM=V-13B, #IT=665K, Representation=Text-based (T)2024.030.825
Vicuna-VTLLM=V-7B, #IT=665K, Representation=Text-based (T)2024.030.82
LLaVA-1.5LLM=V-7B, #PT=558K, #IT=665K, Representation=Visual Embeddings (E)2024.030.819
Vicuna-CapLLM=V-13B, #IT=665K, Representation=Text-based (T)2024.030.792
Vicuna-DCapLLM=V-13B, #IT=665K, Representation=Text-based (T)2024.030.776
Vicuna-SGLLM=V-13B, #IT=665K, Representation=Text-based (T)2024.030.77