List your company

Image Captioning Hallucination Evaluation on COCO Cap Chair

13.2168Chair-IVisPlay
8.0130569.36402810.71512.065972Jun 25, 2026

Evaluation results

MethodLinks
VisPlayModel=Qwen3-VL-2B-Instruct2026.0613.216846.186971.3239
VisPlayModel=Qwen3-VL-4B-Instruct2026.0613.215846.184974.3239
BaseModel=Qwen3-VL-2B-Instruct2026.0613.213345.960172.0939
EvoLMMModel=Qwen3-VL-2B-Instruct2026.0612.985144.223870.9924
iReasonerModel=Qwen3-VL-2B-Instruct2026.0612.983544.220570.9931
BaseModel=Qwen3-VL-4B-Instruct2026.0612.914144.579274.8582
VisionZero-CLEVRModel=Qwen3-VL-4B-Instruct2026.0612.603845.397874.8559
VisionZero-ChartModel=Qwen3-VL-2B-Instruct2026.0612.482343.374171.8795
VisionZero-ChartModel=Qwen3-VL-4B-Instruct2026.0612.206944.402575.1604
EvoLMMModel=Qwen3-VL-4B-Instruct2026.0612.203144.904875.0184
iReasonerModel=Qwen3-VL-4B-Instruct2026.0612.202444.903575.0196
VisionZero-RWModel=Qwen3-VL-4B-Instruct2026.0611.907943.402474.8604
VisionZero-CLEVRModel=Qwen3-VL-2B-Instruct2026.0611.907444.966172.3015
VISEModel=Qwen3-VL-4B-Instruct2026.0611.904143.019775.7404
BaseModel=Qwen3-VL-8B-Instruct2026.0611.204743.423775.4236
VisionZero-ChartModel=Qwen3-VL-8B-Instruct2026.0611.162843.201575.4728
VisionZero-RWModel=Qwen3-VL-8B-Instruct2026.0611.109442.962475.5316
iReasonerModel=Qwen3-VL-8B-Instruct2026.0611.071242.735875.5893
EvoLMMModel=Qwen3-VL-8B-Instruct2026.0611.018742.487275.6441
VisionZero-CLEVRModel=Qwen3-VL-8B-Instruct2026.0610.982942.256475.7014
VisPlayModel=Qwen3-VL-8B-Instruct2026.0610.936442.018675.7562
BaseModel=Qwen3-VL-32B-Instruct2026.0610.854342.632176.5346
VISEModel=Qwen3-VL-8B-Instruct2026.0610.837541.533675.8369
iReasonerModel=Qwen3-VL-32B-Instruct2026.0610.812942.518476.5812
VisPlayModel=Qwen3-VL-32B-Instruct2026.0610.756442.389176.6943
VisionZero-ChartModel=Qwen3-VL-32B-Instruct2026.0610.708542.267876.8125
EvoLMMModel=Qwen3-VL-32B-Instruct2026.0610.652142.134676.9348
VisionZero-RWModel=Qwen3-VL-32B-Instruct2026.0610.599442.003277.0816
VisionZero-CLEVRModel=Qwen3-VL-32B-Instruct2026.0610.546841.926477.2193
VISEModel=Qwen3-VL-32B-Instruct2026.0610.417341.873577.4621
VisionZero-RWModel=Qwen3-VL-2B-Instruct2026.0610.219241.913672.0988
VISEModel=Qwen3-VL-2B-Instruct2026.068.213240.509772.3145