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

GUI Agent Task Completion on OSWorld 1.0 (test)

91.67Success Rate (OS)

Claude Sonnet 4.6

4.653227.244149.83572.4259Jan 7, 2026Feb 2, 2026Mar 1, 2026Mar 28, 2026Apr 24, 2026May 21, 2026Jun 17, 2026
Updated 25d ago

Evaluation Results

MethodLinks
2026.05
91.67-69.2374.4770.2186.83-66.6781.4172.7376.65-----
2026.05
79.17-73.0880.8582.1973.91-8075.7191.379.53-----
2026.05
75-76.2951.0652.9865.22-6064.6565.2263.8-----
2026.05
66.67-82.0541.1350.3555.07-73.3356.8672.4662.24-----
2026.05
61.11-74.3635.4648.2156.52-57.7837.2572.7355.43-----
2026.05
60.83-66.1528.0737.6650.43-65.3345.7151.350.69-----
2026.05
59.42-57.6919.1536.8840.58-66.6747.0662.3248.72-----
2026.01
52.240.555.113.530.739.19.744.42552.829.7-----
2026.01
5041.234.68.529.739.110.833.335.343.527.1-----
2026.01
48.635.569.210.629.837.7935.533.362.329.7-----
2026.01
45.836.934.610.625.430.410.846.729.447.826-----
2026.01
45.836.969.212.829.847.89.74035.365.231.4-----
2026.01
41.734.861.51027.734.884025.555.127.3-----
2026.05
41.67-39.7422.743.9752.17-66.6744.1247.8344.86-----
2026.05
40-48.4611.9131.4930.43-54.6732.9451.337.65-----
2026.01
37.536.946.21736.243.59.766.738.560.931.2-----
2026.01
34.822.951.911.729.739.13.826.734.26324.5-----
2026.01
30.444.446.21331.839.14.866.723.556.528.1-----
2026.06
22----------72.188335856
2026.06
18----------58.478175543
2026.06
18----------46.144255624
2026.06
18----------52.459196528
2026.06
17----------63.381295943
2026.06
16----------61.981295839
2026.06
16----------53.974255723
2026.06
16----------55.175185832
2026.06
15----------35.636204512
2026.06
14----------45.955265219
2026.06
13----------40.539265217
2026.06
13----------53.269195932
2026.06
12----------32.12919479
2026.06
12----------40.146185316
2026.06
12----------24.11713396
2026.06
11----------28.728183413
2026.06
11----------31.34013418
2026.06
11----------3643214213
2026.06
10----------53.172294932
2026.06
10----------32.739154014
2026.06
9----------40.245185518
2026.06
8----------29.63519378
2026.06
8----------30.43419435
2026.06
8----------31.943153711
2026.05
--42.3-22.731.8--35.340.5------
2026.05
--30.844.742.634.7----------
2026.06
-----------78.7----
2026.06
-----------22.7----
2026.06
-----------37.4----
2026.06
----------28-----
2026.06
----------38.1-----
2026.06
----------42.5-----
2026.06
----------42.9-----
2026.06
----------15.2-----
2026.06
----------17-----
2026.06
----------18.8-----
----------20.5-----
2026.06
----------20.6-----
2026.06
----------22.7-----
2026.06
----------24.6-----
2026.06
----------26.9-----
2026.06
----------27-----
----------34.5-----
----------41.4-----
2026.06
----------19-----
----------21.3-----
2026.06
----------34.5-----
----------38.2-----
2026.06
----------42.3-----
----------48.9-----