List your company

GUI Localization on GUIZoom-Bench hard-mislead

54.1Localization AccuracyQwen3-VL-32B
-2.16412.44327.0541.657Dec 5, 2025

Evaluation results

MethodLinks
Qwen3-VL-32BZoom Depth=d42025.1254.1
Qwen3-VL-8BZoom Depth=d42025.1245.9
Qwen3-VL-32BZoom Depth=d22025.1245.9
Qwen3-VL-32BZoom Depth=d32025.1245.9
Qwen3-VL-8BZoom Depth=d32025.1240.5
UI-Venus-7BZoom Depth=d22025.1235.1
UI-Venus-7BZoom Depth=d32025.1235.1
Qwen3-VL-8BZoom Depth=d22025.1232.4
UI-Venus-7BZoom Depth=d42025.1229.7
UI-TARS-7BZoom Depth=d32025.1224.3
UI-TARS-1.5-7BZoom Depth=d22025.1224.3
Qwen3-VL-32BZoom Depth=d12025.1221.6
UI-TARS-1.5-7BZoom Depth=d32025.1221.6
UI-TARS-7BZoom Depth=d42025.1218.9
UI-TARS-1.5-7BZoom Depth=d12025.1218.9
UI-TARS-1.5-7BZoom Depth=d42025.1218.9
UI-Venus-7BZoom Depth=d12025.1218.9
Qwen3-VL-8BZoom Depth=d12025.1216.2
Qwen2.5-VL-7BZoom Depth=d32025.1216.2
Qwen2.5-VL-7BZoom Depth=d42025.1213.5
Qwen2.5-VL-7BZoom Depth=d22025.1210.8
UI-TARS-7BZoom Depth=d22025.1210.8
Claude-4.5-SonnetZoom Depth=d12025.1210.5
GPT-5Zoom Depth=d22025.128.1
GPT-5Zoom Depth=d42025.125.4
UI-TARS-7BZoom Depth=d12025.125.4
GPT-5Zoom Depth=d32025.122.7
GPT-5Zoom Depth=d12025.120
Qwen2.5-VL-7BZoom Depth=d12025.120