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

Agent Task on GTA

24.89Success Rate

PAIR

13.273216.289119.30522.3209May 18, 2026
Updated 15d ago

Evaluation Results

MethodLinks
2026.05
24.89
23.87
2026.05
22.18
2026.05
21.54
2026.05
20.05
19.89
2026.05
19.34
2026.05
18.65
2026.05
18.56
2026.05
18.51
18.12
17.98
17.89
2026.05
17.21
14.32
2026.05
13.72