List your company

Text Visual Question Answering (Open Ended) on RIO-Bench Text-VQA (OE) Attack

85.3Acc (AVG)RIO-RT
9.06828.85948.6568.441Dec 10, 2025

Evaluation results

MethodLinks
RIO-RTBackbone=Qwen-2.5-VL-7B, Category=selective2025.1285.385.285.5
RIO-RTBackbone=Qwen2.5-VL-7B, Training Strategy=RIO-RT2025.1285.3——
RIO-RTBackbone=Qwen-3-VL-7B, Category=selective2025.1285.185.185.1
RIO-RTBackbone=Llama-3.2-Vision-11B, Category=selective2025.1281.781.781.7
RIO-RTBackbone=Llama-3.2-11B-Vision, Training Strategy=RIO-RT2025.1281.7——
pretrainedBackbone=Qwen-3-VL-7B2025.1278.979.378.6
pretrainedBackbone=Qwen-2.5-VL-7B2025.1278.178.977.4
pretrainedBackbone=Qwen2.5-VL-7B, Training Strategy=pretrained2025.1278.1——
IT-RTBackbone=Qwen-2.5-VL-7B, Category=text-agnostic2025.1272.872.972.7
IT-RTBackbone=Qwen2.5-VL-7B, Training Strategy=IT-RT2025.1272.8——
CoT-defenseBackbone=Qwen-3-VL-7B, Category=text-agnostic2025.1270.370.470.1
CoT-defenseBackbone=Qwen-2.5-VL-7B, Category=text-agnostic2025.1268.469.167.7
CoTBackbone=Qwen2.5-VL-7B, Training Strategy=CoT2025.1268.4——
RIO-RTBackbone=SmolVLM-2B, Category=selective2025.1266.566.766.4
pretrainedBackbone=SmolVLM-2B2025.1266.366.566
CoT-defenseBackbone=SmolVLM-2B, Category=text-agnostic2025.1264.66564.2
CoT-defenseBackbone=Llama-3.2-Vision-11B, Category=text-agnostic2025.126363.662.4
CoTBackbone=Llama-3.2-11B-Vision, Training Strategy=CoT2025.1263——
IT-RTBackbone=Qwen-3-VL-7B, Category=text-agnostic2025.1260.961.360.6
pretrainedBackbone=Llama-3.2-Vision-11B2025.1256.25755.4
pretrainedBackbone=Llama-3.2-11B-Vision, Training Strategy=pretrained2025.1256.2——
RIO-RTBackbone=Llava-1.5-7B, Category=selective2025.1253.353.653.1
RIO-RTBackbone=LLaVA-1.5-7B, Training Strategy=RIO-RT2025.1253.3——
RIO-RTBackbone=Llava-1.5-13B, Category=selective2025.1250.550.950
RIO-RTBackbone=LLaVA-1.5-13B, Training Strategy=RIO-RT2025.1250.5——
pretrainedBackbone=Llava-1.5-13B2025.1249.751.148.2
pretrainedBackbone=LLaVA-1.5-13B, Training Strategy=pretrained2025.1249.7——
CoT-defenseBackbone=Llava-1.5-13B, Category=text-agnostic2025.1246.246.945.4
CoTBackbone=LLaVA-1.5-13B, Training Strategy=CoT2025.1246.2——
pretrainedBackbone=Llava-1.5-7B2025.1245.146.244.1
pretrainedBackbone=LLaVA-1.5-7B, Training Strategy=pretrained2025.1245.1——
IT-RTBackbone=Llama-3.2-Vision-11B, Category=text-agnostic2025.1244.444.744.1
IT-RTBackbone=Llama-3.2-11B-Vision, Training Strategy=IT-RT2025.1244.4——
CoT-defenseBackbone=Llava-1.5-7B, Category=text-agnostic2025.1242.143.341
CoTBackbone=LLaVA-1.5-7B, Training Strategy=CoT2025.1242.1——
IT-RTBackbone=SmolVLM-2B, Category=text-agnostic2025.1228.328.528.2
IT-RTBackbone=Llava-1.5-7B, Category=text-agnostic2025.1222.624.221.1
IT-RTBackbone=LLaVA-1.5-7B, Training Strategy=IT-RT2025.1222.6——
IT-RTBackbone=Llava-1.5-13B, Category=text-agnostic2025.121212.611.4
IT-RTBackbone=LLaVA-1.5-13B, Training Strategy=IT-RT2025.1212——