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

Evaluator Accuracy on AndroidBench

94.9Overall Accuracy

GUIDE

69.21275.88182.5589.219Apr 6, 2026
Updated 12d ago

Evaluation Results

MethodLinks
2026.04
94.985.698.110095.8
92.9----
2026.04
92.683.693.310093.3
2026.04
92.486.193.999.290.3
2026.04
90.6----
2026.04
89.8----
2026.04
70.2----