Our new X account is live! Follow @wizwand_team for updates

Function Selection on TaskBench DailyLife

96.8Function Selection Accuracy

Raw Demonstrations

Updated 4d ago

Evaluation Results

Method	Links
Raw Demonstrations 2025.12		96.8
Raw Demonstrations 2025.12		96.6
No ICL 2025.12		96.6
No ICL 2025.12		96.2
Raw Demonstrations 2025.12		94.5
No ICL 2025.12		93.9
DTDR-L 2025.12		93.7
DTDR-L 2025.12		91.5
DTDR-L 2025.12		91
DTDR-L 2025.12		89
Raw Demonstrations 2025.12		87.6
Dependency Retrieval 2025.12		84.1
DTDR-C 2025.12		84.1
No ICL 2025.12		83.5
DTDR-L 2025.12		83.1
Dependency Retrieval 2025.12		82.9
DTDR-C 2025.12		82.9
Dependency Retrieval 2025.12		75.3
DTDR-C 2025.12		75.3
Raw Demonstrations 2025.12		69
No ICL 2025.12		66.7
Dependency Retrieval 2025.12		64.7
DTDR-C 2025.12		64.7
Learned Retrieval 2025.12		60.4
DTDR-C 2025.12		60.2
Dependency Retrieval 2025.12		60
Learned Retrieval 2025.12		56.6
Learned Retrieval 2025.12		56.5
Learned Retrieval 2025.12		52.2
Learned Retrieval 2025.12		48.1
DTDR-L 2025.12		45.9
DTDR-C 2025.12		23.7
Learned Retrieval 2025.12		19.6
No ICL 2025.12		12.8
Dependency Retrieval 2025.12		11.5
Raw Demonstrations 2025.12		10.5