Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

GUI Grounding on MMBench-GUI L2 (test)

2.9Average Error

GPT-4o

-0.63623.23247.170.968Nov 2, 2025Nov 18, 2025Dec 4, 2025Dec 20, 2025Jan 5, 2026Jan 21, 2026Feb 6, 2026
Updated 20d ago

Evaluation Results

MethodLinks
2026.02
2.91.51.18.74.31.115.13.32.51.43.22.9--
2025.12
2.91.51.18.74.31.115.13.32.51.43.22.9--
2026.02
4.71.50.712.57.51.1013.710.61.41.43.22.3--
2025.12
4.71.50.712.57.51.1013.710.61.41.43.22.3--
2025.11
33.9------------3829.8
2026.02
41.436.918.844.421.731.413.374.848.869.646.861.335.4--
2025.12
41.436.918.844.421.731.413.374.848.869.646.861.335.4--
2025.11
41.4------------52.830.1
2026.02
45.737.321.748.133.333.52567.565.2615161.645.5--
2025.12
45.737.321.748.133.333.52567.565.2615161.645.5--
2025.11
45.7--------------
2026.02
46.581.9080.346.267.5090.8091088.10--
2025.12
46.581.9080.346.267.5090.8091088.10--
2026.02
5843.936.858.856.153.930.177.459.179.570.174.858.8--
5843.936.858.856.153.930.177.459.179.570.174.858.8--
2026.02
64.368.3396944.564.437.888.569.490.569.38156.5--
2025.12
64.368.3396944.564.437.888.569.490.569.38156.5--
2025.11
64.3------------78.450.4
2026.02
65.766.83971.348.656.531.192.770.993.57188.764.6--
2025.12
65.766.83971.348.656.531.192.770.993.57188.764.6--
2025.11
65.7------------78.453
2025.11
69.5------------84.354.9
2025.11
69.8--------------
2025.11
70.4--------------
2025.11
70.9--------------
2026.02
72.270.142.675.752.359.241.393.680.692.778.690.765.9--
2025.12
72.270.142.675.752.359.241.393.680.692.778.690.765.9--
2025.11
73.4------------84.162.9
2026.02
74.378.651.880.362.768.651.590.881.2938088.168.5--
2025.12
74.378.651.880.362.768.651.590.881.2938088.168.5--
2025.11
75.5------------86.564.5
2025.11
76.3------------86.266.5
2026.02
76.580.855.181.460.464.941.894.382.793.579.789.772.1--
2025.12
76.580.855.181.460.464.941.894.382.793.579.789.772.1--
2026.02
76.677.557.777.160.768.644.995.58095.583.789.768.8--
2025.12
76.677.557.777.160.768.644.995.58095.583.789.768.8--
2025.11
77.1------------87.367.1
2026.02
78.576.857.480.363.968.653.693.983.396.384.590.374.7--
2025.12
78.576.857.480.363.968.653.693.983.396.384.590.374.7--
2026.02
78.879.755.179.764.769.65095.282.796.685.491.975.6--
2025.12
78.879.755.179.764.769.65095.282.796.685.491.975.6--
2025.11
79.1------------88.369.9
2025.11
79.4--------------
2025.11
79.5--------------
2026.02
80.586.461.881.764.574.461.794.98395.883.793.272.7--
2025.12
80.586.461.881.764.574.461.794.98395.883.793.272.7--
2026.02
80.882.761.883.863.972.35294.989.495.285.693.576.3--
2025.12
80.882.761.883.863.972.35294.989.495.285.693.576.3--
2025.11
80.8------------88.373.3
2026.02
81.388.661.885.569.174.953.195.282.495.584.596.872.1--
2025.12
81.388.661.885.569.174.953.195.282.495.584.596.872.1--
2025.11
81.4------------90.272.7
2026.02
82.684.96489.372.575.460.295.285.296.384.292.976--
2025.12
82.684.96489.372.575.460.295.285.296.384.292.976--
2026.02
8385.665.184.967.17763.395.285.596.18795.580.8--
2025.12
8385.665.184.967.17763.395.285.596.18795.580.8--
2026.02
83.482.366.9897473.35296.288.295.888.595.279.9--
2025.12
83.482.366.9897473.35296.288.295.888.595.279.9--
2025.11
83.7------------9176.5
2025.11
84.5------------91.777.4
2026.02
85.393.471.392.874.37856.195.588.897.288.592.678.6--
2025.12
85.393.471.392.874.37856.195.588.897.288.592.678.6--
2025.11
86.8------------92.880.7
2026.02
8793.768.487.575.785.969.997.188.897.290.195.884.4--
2026.02
88.892.374.390.786.481.267.397.19097.592.795.886--
2025.12
88.892.374.390.786.481.267.397.19097.592.795.886--
2025.12
91.39378.792.887.686.977.697.192.49893.296.192.5--