List your company

Robust GUI Navigation on GUI-RobustEval

55.8Success Rate (Depth 0)Jedi-7B w/ GPT 5.1
3.07216.76130.4544.139May 28, 2026

Evaluation results

MethodLinks
Jedi-7B w/ GPT 5.1Model Category=Proprietary Models2026.0555.844.232.229.134.6
Qwen3-VL-PlusModel Category=Proprietary Models2026.0555.146.136.933.565.4
Qwen3-VL-FlashModel Category=Proprietary Models2026.0554.944.634.532.163.9
RoTS-32BModel Category=Open-Source Models2026.0549.741.836.533.258.8
Qwen3-VL-8B-InstructModel Category=Open-Source Models2026.0548.138.73025—
OpenCUA-32BModel Category=Open-Source Models2026.0545.537.228.625.950.3
RoTS-7BModel Category=Open-Source Models2026.0543.536.630.126.751.9
OpenCUA-7BModel Category=Open-Source Models2026.0540.730.323.31946.3
UI-TARS1.5-7BModel Category=Open-Source Models2026.0539.634.227.823.338
GUI-Owl-7BModel Category=Open-Source Models2026.0528.715.68.110.45.9
GPT 5.1Model Category=Proprietary Models2026.0523.416.513.111.233.9
Qwen2.5-VL-7B-InstructModel Category=Open-Source Models2026.055.132.91.3—