List your company
ResearchFormerly WizWand

Object Visual Question Answering (Open Ended) on RIO-Bench Obj-VQA (OE) Clean

62.2AccuracyIT-RT
48.6852.1955.759.21Dec 10, 2025
Updated 8mo ago

Evaluation results

MethodLinks
IT-RTBackbone=Llama-3.2-Vision-11B, Category=text-agnostic2025.1262.2
RIO-RTBackbone=Qwen-2.5-VL-7B, Category=selective2025.1261.5
RIO-RTBackbone=Llama-3.2-Vision-11B, Category=selective2025.1261.5
IT-RTBackbone=Qwen-2.5-VL-7B, Category=text-agnostic2025.1261.3
IT-RTBackbone=Qwen-3-VL-7B, Category=text-agnostic2025.1261.1
IT-RTBackbone=Llava-1.5-7B, Category=text-agnostic2025.1260.9
RIO-RTBackbone=Llava-1.5-7B, Category=selective2025.1260.5
IT-RTBackbone=Llava-1.5-13B, Category=text-agnostic2025.1260.1
RIO-RTBackbone=Qwen-3-VL-7B, Category=selective2025.1260
CoT-defenseBackbone=Qwen-3-VL-7B, Category=text-agnostic2025.1259.8
CoT-defenseBackbone=Llama-3.2-Vision-11B, Category=text-agnostic2025.1259.8
pretrainedBackbone=Qwen-2.5-VL-7B2025.1259.6
RIO-RTBackbone=Llava-1.5-13B, Category=selective2025.1259.3
CoT-defenseBackbone=Qwen-2.5-VL-7B, Category=text-agnostic2025.1259
pretrainedBackbone=Qwen-3-VL-7B2025.1258.7
CoT-defenseBackbone=Llava-1.5-13B, Category=text-agnostic2025.1258.5
IT-RTBackbone=SmolVLM-2B, Category=text-agnostic2025.1258.1
RIO-RTBackbone=SmolVLM-2B, Category=selective2025.1258.1
CoT-defenseBackbone=Llava-1.5-7B, Category=text-agnostic2025.1257.8
pretrainedBackbone=Llama-3.2-Vision-11B2025.1257.6
pretrainedBackbone=Llava-1.5-13B2025.1256.5
pretrainedBackbone=Llava-1.5-7B2025.1256
pretrainedBackbone=SmolVLM-2B2025.1253.7
CoT-defenseBackbone=SmolVLM-2B, Category=text-agnostic2025.1249.2