Function Calling
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
75AUROC
8
Apr 28, 2026
77AUROC
8
Apr 28, 2026
76AUROC
8
Apr 28, 2026
0.72AUROC
8
Apr 28, 2026
0.76AUROC
8
Apr 28, 2026
0.77AUROC
8
Apr 28, 2026
84.5Accuracy
8
Apr 3, 2026
1Spearman Rho (FullPair Agreement)
7
May 29, 2026
96Non-Live Multiple AST Success Rate
7
Mar 13, 2026
36.6Accuracy
7
Feb 26, 2026
80.1Accuracy
6
Jul 9, 2026
88.6Accuracy
6
Jul 9, 2026
53.8Score
6
May 28, 2026
70.1Score
6
May 28, 2026
60Base Success Rate
6
Apr 24, 2026
70Accuracy
6
Jun 26, 2026
86.48Non-Live Score
6
Mar 13, 2026
80.23Simple Success Rate
6
Mar 13, 2026
74.92Simple Success Rate
6
Mar 13, 2026
68.92Overall Success
5
May 19, 2026
86.2Accuracy
5
Mar 4, 2026
46Success Rate
5
Feb 26, 2026
50Success Rate
5
Feb 26, 2026
68.14Accuracy
5
Feb 26, 2026
69Success Rate
4
Jun 26, 2026