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

GUI Automation on OSWorld Verified (test)

61.92Overall Success Rate

Seed-1.8

2.099217.629633.1648.6904Oct 20, 2025Nov 7, 2025Nov 26, 2025Dec 15, 2025Jan 3, 2026Jan 22, 2026Feb 10, 2026
Updated 7d ago

Evaluation Results

MethodLinks
2026.02
61.926353.872.36882.54970.86058.273.9
2026.02
58.156.457.76657.565.24770.866.752.969.6
2025.10
43.7----------
2025.10
41.5----------
2025.10
41----------
2025.10
39----------
2026.02
36.639.176.925.529.847.815.154.253.347.160.9
2025.10
35.8----------
2025.10
35.1----------
2026.02
34.628.376.927.740.443.51458.333.341.247.8
2025.10
34.5----------
2025.10
34.1----------
2025.10
33.3----------
2025.10
31.3----------
2025.10
30.2----------
2025.10
29.7----------
2026.02
28.941.25013.927.155.410.63733.643.346.7
2025.10
28.9----------
2025.10
28.5----------
2025.10
28.2----------
2025.10
27.3----------
2025.10
27.1----------
2025.10
27----------
2025.10
27----------
2025.10
27----------
2025.10
26.8----------
2025.10
26.1----------
2025.10
26----------
2025.10
25.8----------
2026.02
25.128.8504.336.139.19.82546.718.847.8
2025.10
24.5----------
2026.02
24.336.95010.636.126.16.529.253.329.443.5
2025.10
24.3----------
2025.10
24----------
2025.10
23.4----------
2025.10
17.2----------
2026.02
15----------
2025.10
9.1----------
2026.02
5.58.711.5004.31.18.36.717.621.7
2025.10
4.4----------