List your company
ResearchFormerly WizWand

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

84.6Accuracypretrained
12.52831.23949.9568.661Dec 10, 2025
Updated 8mo ago

Evaluation results

MethodLinks
pretrainedBackbone=Qwen-2.5-VL-7B2025.1284.6
pretrainedBackbone=Qwen2.5-VL-7B, Training Strategy=pretrained2025.1284.6
RIO-RTBackbone=Qwen-2.5-VL-7B, Category=selective2025.1284.3
RIO-RTBackbone=Qwen2.5-VL-7B, Training Strategy=RIO-RT2025.1284.3
RIO-RTBackbone=Qwen-3-VL-7B, Category=selective2025.1284.1
pretrainedBackbone=Qwen-3-VL-7B2025.1284
RIO-RTBackbone=Llama-3.2-Vision-11B, Category=selective2025.1281.3
RIO-RTBackbone=Llama-3.2-11B-Vision, Training Strategy=RIO-RT2025.1281.3
IT-RTBackbone=Qwen-2.5-VL-7B, Category=text-agnostic2025.1280.9
IT-RTBackbone=Qwen2.5-VL-7B, Training Strategy=IT-RT2025.1280.9
pretrainedBackbone=SmolVLM-2B2025.1272.3
CoT-defenseBackbone=Qwen-3-VL-7B, Category=text-agnostic2025.1272.1
CoT-defenseBackbone=Qwen-2.5-VL-7B, Category=text-agnostic2025.1271.4
CoTBackbone=Qwen2.5-VL-7B, Training Strategy=CoT2025.1271.4
CoT-defenseBackbone=SmolVLM-2B, Category=text-agnostic2025.1271.1
CoT-defenseBackbone=Llama-3.2-Vision-11B, Category=text-agnostic2025.1270
CoTBackbone=Llama-3.2-11B-Vision, Training Strategy=CoT2025.1270
RIO-RTBackbone=SmolVLM-2B, Category=selective2025.1268.9
IT-RTBackbone=Qwen-3-VL-7B, Category=text-agnostic2025.1268.5
pretrainedBackbone=Llama-3.2-Vision-11B2025.1265.5
pretrainedBackbone=Llama-3.2-11B-Vision, Training Strategy=pretrained2025.1265.5
IT-RTBackbone=Llama-3.2-Vision-11B, Category=text-agnostic2025.1258.5
IT-RTBackbone=Llama-3.2-11B-Vision, Training Strategy=IT-RT2025.1258.5
pretrainedBackbone=Llava-1.5-13B2025.1254.5
pretrainedBackbone=LLaVA-1.5-13B, Training Strategy=pretrained2025.1254.5
RIO-RTBackbone=Llava-1.5-7B, Category=selective2025.1253.3
RIO-RTBackbone=LLaVA-1.5-7B, Training Strategy=RIO-RT2025.1253.3
RIO-RTBackbone=Llava-1.5-13B, Category=selective2025.1253.2
RIO-RTBackbone=LLaVA-1.5-13B, Training Strategy=RIO-RT2025.1253.2
CoT-defenseBackbone=Llava-1.5-13B, Category=text-agnostic2025.1250.5
CoTBackbone=LLaVA-1.5-13B, Training Strategy=CoT2025.1250.5
pretrainedBackbone=Llava-1.5-7B2025.1249.5
pretrainedBackbone=LLaVA-1.5-7B, Training Strategy=pretrained2025.1249.5
CoT-defenseBackbone=Llava-1.5-7B, Category=text-agnostic2025.1246.1
CoTBackbone=LLaVA-1.5-7B, Training Strategy=CoT2025.1246.1
IT-RTBackbone=SmolVLM-2B, Category=text-agnostic2025.1235.4
IT-RTBackbone=Llava-1.5-7B, Category=text-agnostic2025.1230.3
IT-RTBackbone=LLaVA-1.5-7B, Training Strategy=IT-RT2025.1230.3
IT-RTBackbone=Llava-1.5-13B, Category=text-agnostic2025.1215.3
IT-RTBackbone=LLaVA-1.5-13B, Training Strategy=IT-RT2025.1215.3