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

Task Success on OSWorld (test)

25Chrome Success Rate

Compressed-a11y

3.689.21514.7520.285May 1, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2523.14.319.130.410.837.546.729.434.820.7
18.219.2014.98.710.833.326.729.430.415.6
13.619.22.219.18.710.833.313.317.634.815.1
2026.05
4.511.502.14.310.820.8011.84.37