List your company

Visual Grounding on HR-Bench 4K

96.2Accuracy (Single)LazyMCoT
68.95276.02683.190.174Jun 15, 2026

Evaluation results

MethodLinks
LazyMCoTBackbone=Qwen2.5-VL-7B-Instruct, Training Free=true2026.0696.25977.6
HiDeBackbone=Qwen2.5-VL-7B-Instruct, Training Free=true2026.0695.559.377.4
LazyMCoTBackbone=Qwen3-VL-8B-Instruct, Training Free=true2026.0694.366.580.4
DeepEyesBackbone=Qwen2.5-VL-7B-Instruct, Training Free=false2026.0691.35975.1
Thyme-VLBackbone=Qwen2.5-VL-7B-Instruct, Training Free=false2026.06916377
Base (Qwen3-VL-8B-Instruct)Backbone=Qwen3-VL-8B-Instruct, Training Free=false2026.0690.566.378.4
ViCropBackbone=Qwen2.5-VL-7B-Instruct, Training Free=true2026.0690.557.574
DeepScanBackbone=Qwen2.5-VL-7B-Instruct, Training Free=true2026.0690.159.775
LazyMCoTBackbone=InternVL3-8B-Instruct, Training Free=true2026.0689.558.874.1
TreeVGRBackbone=Qwen2.5-VL-7B-Instruct, Training Free=false2026.0689.561.572.7
DyfoBackbone=Qwen2.5-VL-7B-Instruct, Training Free=true2026.0689.253.571.3
Base (Qwen2.5-VL-7B-Instruct)Backbone=Qwen2.5-VL-7B-Instruct, Training Free=false2026.0688.854.871.8
HiDeBackbone=InternVL3-8B-Instruct, Training Free=true2026.0688.557.573
ZoomRefineBackbone=Qwen2.5-VL-7B-Instruct, Training Free=true2026.0688.555.371.5
ViCropBackbone=InternVL3-8B-Instruct, Training Free=true2026.06885772.5
Base (InternVL3-8B-Instruct)Backbone=InternVL3-8B-Instruct, Training Free=false2026.0682.858.870.8
GPT-4oTraining Free=true2026.06704859