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

Tool Calling on WHEN2TOOL Overall

-1Δ Accuracy

Necessary (N)

-29.808-22.329-14.85-7.371May 10, 2026
Updated 22d ago

Evaluation Results

MethodLinks
2026.05
-1-0.06-16.8
2026.05
-1.7-0.48-3.6
2026.05
-8.4-0.46-18.4
2026.05
-15.8-0.82-19.2
2026.05
-19.7-1-19.6
2026.05
-24.2-1.08-22.4
2026.05
-28.7-0.71-40.5