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

Interactive Desktop Task Success on OSWorld

50.11Overall Success Rate

Gemini 1.5 Pro + MMSkills

9.206819.825930.44541.0641May 13, 2026May 19, 2026May 26, 2026Jun 2, 2026Jun 9, 2026Jun 16, 2026Jun 23, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.05
50.1159.915053.1953.1960.8624.1170.8366.6770.5965.22
2026.05
47.9755.3742.3153.1940.3456.5230.987566.6752.9460.87
2026.05
46.5957.6942.3140.4348.9260.8623.479.1773.3341.1869.57
2026.05
44.0853.4734.6257.4540.4347.8231.9754.174035.2956.52
2026.06
43.2----------
2026.06
41.8----------
2026.05
40.7644.3534.6238.340.3456.5222.3870.8366.6741.1856.52
2026.05
40.2751.0223.0838.33456.5219.1654.176058.8252.17
2026.06
39.9----------
2026.05
39.6657.694040.4336.1417.3822.3862.553.3358.8243.48
2026.05
39.1759.9169.2323.432.0147.8219.3541.6773.3341.1856.52
2026.05
38.5151.0253.8531.9131.8343.4722.2666.674023.5365.22
2026.06
38.5----------
2026.05
36.6537.785038.329.7352.1721.5154.1766.6752.3947.83
2026.05
36.6153.2453.8531.9131.9852.1720.2420.8346.6735.2965.22
2026.05
34.9851.0234.6234.0435.3230.4314.8654.1766.6732.652.17
2026.05
28.7137.7819.2321.2829.726.0818.754.1753.3311.7647.83
2026.05
28.5742.225010.6421.3134.7814.8633.336035.2947.83
2026.06
28.3----------
2026.05
25.439.9142.318.5123.3717.3913.43256029.4147.83
2026.05
21.3415.5638.4617.0225.5343.489.482526.6717.6534.78
2026.05
14.9319.9111.546.3816.9917.397.3316.6733.3317.6534.78
2026.05
10.7815.477.692.138.594.347.332513.3329.4117.39