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

Tool Use on APT-Bench

65.8Accuracy

Qwen3

56.33658.79361.2563.707Dec 31, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2025.12
65.8
2025.12
64.2
2025.12
64.1
2025.12
61.7
2025.12
59.1
2025.12
56.7