List your company

GUI Navigation on AITW

67.3Overall Success RateQwen-GUI
5.336821.423437.5153.5966Jun 17, 2024Oct 18, 2024Feb 19, 2025Jun 23, 2025Oct 24, 2025Feb 25, 2026Jun 29, 2026

Evaluation results

MethodLinks
Qwen-GUI2024.0667.370.361.271.666.1————————
Qwen-VL2024.0665.870.457.870.164.7————————
SeeClick2024.0660.666.454.963.557.6————————
NaviMastertraining_data=GUI + Embodied2025.0859.72————74.92———————
MiniCPM-GUI2024.0658.462.346.567.357.5————————
NaviMastertraining_data=GUI only2025.0858.05————71.31———————
OmniParser (w. LS + ID)Model Source=Close-Source Model, Evaluation Protocol=Zero-shot2026.0657.757.851.677.452.9—48.3——————
GUI-R1-7B2025.0855.31————62.94———————
UI-shift2025.0854.38————74.44———————
Aguvis2025.0853.06————69.57———————
GPT-4V + historyModel Source=Close-Source Model, Evaluation Protocol=Zero-shot2026.0652.9646.1449.1878.2948.18—43.01——————
GUICrafter–3BModel Source=Open-Source Model, Evaluation Protocol=Zero-shot2026.0650.8954.2951.8661.4640.25—46.57——————
GUICrafter–3BModel Source=Open-Source Model, Evaluation Protocol=Zero-shot, Training Stage=only Stage22026.0649.9252.1152.3658.8441.28—45——————
NaviMastertraining_data=Embodied only2025.0849.17————74.95———————
MiniCPM-V2024.0648.950.245.156.244————————
GoClick-L w/ Intent Gnd.Planner=GPT-4o, Grounding Model=GoClick-L w/ Intent Gnd.2026.0448.95049.754.444.5—45.957.45957.169.760.559.7
Qwen2.5VL-7Bvariant=*2025.0848.81————62.51———————
UI-AGILE2025.0848.66————75.72———————
GUICrafter–3BModel Source=Open-Source Model, Evaluation Protocol=Zero-shot, Reward Strategy=Binary Reward2026.0648.5152.2851.1557.6836.99—44.44——————
GoClick-L w/ Func. Gnd.Planner=GPT-4o, Grounding Model=GoClick-L w/ Func. Gnd.2026.0447.647.147.953.544—45.756.951.254.167.459.757.5
GoClick-L w/ Intent Gnd.Planner=Gemini-2-Flash-Exp, Grounding Model=GoClick-L w/ Intent Gnd.2026.0447.244.149.559.739.8—43.148.152.954.667.454.854
infiGUI-3B2025.0846.51————75.58———————
GoClick-L w/ Func. Gnd.Planner=Gemini-2-Flash-Exp, Grounding Model=GoClick-L w/ Func. Gnd.2026.0446.440.948.559.440—43.248.447.452.966.85552.5
Qwen2.5VL-7B2025.0845.8————65.99———————
Fuyu-GUI2024.0645.550.941.645.743.8————————
GUI-R1-3BModel Source=Open-Source Model, Evaluation Protocol=Zero-shot2026.0643.644.8739.9754.0635.6—43.48——————
Fuyu-8B2024.0643.545.94047.240.8————————
GPT-4o + SoMPlanner=GPT-4o + SoM, Grounding Model=None2026.0442.143.241.45339.2—33.737.253.851.863.25150.4
OS-Atlas-7B2025.0841.38————64.89———————
PalM2-CoTModel Source=Close-Source Model, Evaluation Protocol=Zero-shot2026.0639.6————————————
ShowUI-2BModel Source=Open-Source Model, Evaluation Protocol=Zero-shot2026.0635.947.74220.137.4—32.1——————
Gemini-2-Flash-Exp + SoMPlanner=Gemini-2-Flash-Exp + SoM, Grounding Model=None2026.0434.833.933.948.527.9—29.932.241.430.156.837.838.3
GUICrafter–3BModel Source=Open-Source Model, Evaluation Protocol=Zero-shot, Training Stage=only Stage12026.0631.5334.0732.7336.2624.5—30.09——————
Gemini-2-Flash-ExpPlanner=Gemini-2-Flash-Exp, Grounding Model=None2026.0429.528.530.341.920.2—26.418.226.922.92922.723.6
Qwen2.5-VL-3BModel Source=Open-Source Model, Evaluation Protocol=Zero-shot2026.0628.1428.5822.9737.2824.3—27.57——————
GPT-4oPlanner=GPT-4o, Grounding Model=None2026.0427.232.931.944.225.9—28.224.930.127.647.13029.9
GPT-4o2025.0826.07————35.75———————
ChatGPT-CoTModel Source=Close-Source Model, Evaluation Protocol=Zero-shot2026.067.724.3810.479.398.42—5.93——————