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

GUI Agent Planning and Execution on WebArena

70Success Rate (Gitlab)

WEBXSKILL (Grounded)

-1.645616.954735.55554.1553Mar 12, 2026Mar 17, 2026Mar 23, 2026Mar 28, 2026Apr 3, 2026Apr 8, 2026Apr 14, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2026.04
7057.710069.565.965.7
2026.04
66.753.968.459.756.857.1
2026.04
63.3507959.75065.7
2026.04
63.361.589.568.859.180
2026.04
6046.284.26352.380
2026.04
56.75084.262.352.377.1
2026.04
53.330.863.243.536.442.9
2026.04
51.828.157.742.930.947.4
2026.04
5046.257.944.231.845.7
2026.04
5046.257.944.231.845.7
2026.04
5057.763.253.947.757.1
2026.04
46.738.547.448.747.760
2026.04
44.441.330.237.428.342.9
2026.04
43.342.357.945.540.948.6
2026.04
43.346.273.747.138.647.1
2026.04
4046.266.743.837.838.7
2026.03
32.146.4227.3622.82--
2026.03
27.8124.7720.1924.87--
2026.03
2521.122.7723.28--
2026.03
22.7320.1917.9220.6--
2026.03
15.87515.6312.81--
2026.03
9.52505.72--
2026.03
9.527.506.41--
2026.03
7.947.53.136.53--
2026.03
7.9406.255.3--
2026.03
6.352.503.58--
2026.03
6.35109.348.16--
2026.03
6.3556.255.95--
2026.03
4.847.53.135.12--
2026.03
1.370.950.971.13--
2026.03
1.140.981.961.32--
2026.03
1.1100.940.76--