List your company
ResearchFormerly WizWand

Visual Question Answering on E-VQA (Single-Hop/All metrics)

55.9Accuracy (Single-Hop)MMAgent-R2
10.1422.0233.945.78Aug 7, 2025Oct 1, 2025Nov 26, 2025Jan 21, 2026Mar 18, 2026May 13, 2026Jul 8, 2026
Updated 3mo ago

Evaluation results

MethodLinks
MMAgent-R2Model=Qwen3-VL-8B, Retriever=EVA-CLIP-8B2026.0755.954.2
MMAgent-R2Model=Qwen2.5-VL-7B, Retriever=EVA-CLIP-8B2026.0755.453.6
QKVQAModel=Qwen2.5-VL-7B, Retriever=EVA-CLIP-8B2026.0753.7—
QKVQAModel=LLaMA-3.1-8B, Retriever=EVA-CLIP-8B2026.0749.5—
ReAGModel=Qwen2.5-VL-7B, Retriever=EVA-CLIP-8B2026.0744.947
EchoSightModel=Mistral-7B/LLaMA3-8B, Retriever=EVA-CLIP-8B2026.0741.8—
VLM-PRFModel=InternVL3-8B, Retriever=EVA-CLIP-8B2026.0740.139.2
MMKB-RAGModel=Qwen2-7B, Retriever=EVA-CLIP-8B2026.0739.735.9
mKG-RAGLLM / MLLM=LLaMA-3.1-8B, Retriever=QM-Retriever, Retrieval Mode (Text)=true, Retrieval Mode (Vision)=true, Fine-tuning=true2025.0838.436.3
mKG-RAGModel=LLaVA-MORE-8B, Retriever=Custom VLM2026.0738.436.3
mKG-RAGLLM / MLLM=LLaMA-3.1-8B, Retriever=CLIP ViT-L/14, Retrieval Mode (Text)=true, Retrieval Mode (Vision)=false, Variant=text-only, Fine-tuning=true2025.0836.634.9
ReflectiVALLM / MLLM=LLaMA-3.1-8B, Retriever=EVA-CLIP-8B, Retrieval Mode (Text)=false, Retrieval Mode (Vision)=true, Variant=vision-only, Fine-tuning=true2025.0835.535.5
mKG-RAGLLM / MLLM=LLaMA-3.1-8B, Retriever=CLIP ViT-L/14, Retrieval Mode (Text)=false, Retrieval Mode (Vision)=true, Variant=vision-only, Fine-tuning=true2025.0832.931
DPRv+tModel=Multi-passage BERT, Retriever=CLIP ViT-B/322026.0729.1—
ReflectiVALLM / MLLM=LLaMA-3.1-8B, Retriever=EVA-CLIP-8B, Retrieval Mode (Text)=true, Retrieval Mode (Vision)=false, Variant=text-only, Fine-tuning=true2025.082829.2
mKG-RAGLLM / MLLM=LLaMA-3.1-8B, Retriever=QM-Retriever, Retrieval Mode (Text)=true, Retrieval Mode (Vision)=true2025.0827.126.1
GPT-4V2026.0726.928.1
EchoSightLLM / MLLM=LLaMA-3.1-8B, Retriever=EVA-CLIP-8B, Retrieval Mode (Text)=false, Retrieval Mode (Vision)=true, Variant=vision-only2025.0826.424.9
RAG-AnythingLLM / MLLM=LLaMA-3.1-8B, Retriever=text-embedding-3-small, Retrieval Mode (Text)=true, Retrieval Mode (Vision)=false2025.0825.624.8
mKG-RAGLLM / MLLM=LLaMA-3.1-8B, Retriever=CLIP ViT-L/14, Retrieval Mode (Text)=false, Retrieval Mode (Vision)=true, Variant=vision-only2025.0824.623.7
mKG-RAGLLM / MLLM=LLaMA-3.1-8B, Retriever=CLIP ViT-L/14, Retrieval Mode (Text)=true, Retrieval Mode (Vision)=false, Variant=text-only2025.0824.423.4
RA-VQA-v2LLM / MLLM=T5-large, Retriever=ColBERT & CLIP, Retrieval Mode (Text)=true, Retrieval Mode (Vision)=false, Fine-tuning=true2025.0822.421.5
EchoSightLLM / MLLM=LLaMA-3.1-8B, Retriever=EVA-CLIP-8B, Retrieval Mode (Text)=true, Retrieval Mode (Vision)=false, Variant=text-only2025.0822.421.7
Wiki-LLaVALLM / MLLM=Vicuna-7B, Retriever=CLIP ViT-L/14, Retrieval Mode (Text)=true, Retrieval Mode (Vision)=false, Fine-tuning=true2025.0821.826.4
RA-VQALLM / MLLM=T5-large, Retriever=BERT-base, Retrieval Mode (Text)=true, Retrieval Mode (Vision)=false, Fine-tuning=true2025.0821.720
Qwen3-VL-8BModel=Qwen3-VL-8B2026.0720.320.5
Qwen2-VLLLM / MLLM=Qwen2-VL-7B, Retriever=None, Retrieval Mode (Text)=false, Retrieval Mode (Vision)=false2025.0819.919.7
Qwen2.5-VL-7BModel=Qwen2.5-VL-7B2026.071918.8
Wiki-LLaVAModel=LLaVA-v1.5-7B, Retriever=CLIP ViT-L/142026.0717.720.3
LLaVA-v1.5LLM / MLLM=Vicuna-7B, Retriever=None, Retrieval Mode (Text)=false, Retrieval Mode (Vision)=false2025.0816.316.9
LLaVA-MORELLM / MLLM=LLaMA-3.1-8B, Retriever=None, Retrieval Mode (Text)=false, Retrieval Mode (Vision)=false2025.0815.816
BLIP-2LLM / MLLM=Flan-T5XL, Retriever=None, Retrieval Mode (Text)=false, Retrieval Mode (Vision)=false2025.0812.612.4
BLIP-2Model=Flan-T5XL2026.0712.612.4
InstructBLIPModel=Flan-T5XL2026.0711.912
RORA-VLMLLM / MLLM=Vicuna-7B, Retriever=CLIP & GS, Retrieval Mode (Text)=false, Retrieval Mode (Vision)=true2025.08—20.3
RORA-VLMModel=LLaVA-v1.5-7B, Retriever=CLIP ViT-L/142026.07—20.3