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

Terminal Task Execution on Terminal-Bench 2.0

59.6Success Rate

HarnessBridge-D

-1.65614.24730.1546.053Jun 11, 2026Jun 13, 2026Jun 15, 2026Jun 17, 2026Jun 19, 2026Jun 21, 2026Jun 23, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
59.60.98
2026.06
57.31.02
2026.06
53.99.41
2026.06
52.80.51
2026.06
51.70.92
2026.06
49.42.18
2026.06
23.61
2026.06
189.8
2026.06
13.5-
2026.06
13.1-
2026.06
10.9-
2026.06
8.2-
2026.06
7.9-
2026.06
2.2-
2026.06
0.7-