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

Tool-calling on BFCL Standard Setting

86.46Non-Live Accuracy

All_Funs

64.443270.159175.87581.5909Mar 12, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
86.4667.4476.95
2026.03
85.8178.0281.92
2026.03
84.9876.2480.61
2026.03
84.7374.8379.78
2026.03
84.675.580.05
2026.03
79.2369.1374.18
2026.03
78.963.871.35
2026.03
78.5466.6272.58
2026.03
78.0863.5170.8
2026.03
7866.0372.02
2026.03
77.7368.0272.88
2026.03
77.6363.4370.53
2026.03
76.3563.870.08
2026.03
75.5661.5168.54
2026.03
70.9662.7766.87
2026.03
69.9658.1864.07
2026.03
68.9457.2263.08
2026.03
65.2952.2658.78