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

Function Calling on Mobile Actions

84.5Overall Accuracy

ST-Qwen3-4B

55.58863.09470.678.106Feb 4, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
84.5---99.9
2026.02
83.2---100
2026.02
81.4---99.9
2026.02
80.5---100
2026.02
72.8---100
2026.02
69.3---99.3
2026.02
68.4---77.2
2026.02
68---75
2026.02
67---75
2026.02
66.2---75
2026.02
65.5---74.9
2026.02
56.7---74.4
2026.02
-468.56671-
2026.02
-110.11544.3-
2026.02
-61.1139.57.7-
2026.02
-5174.59.2-