Function Calling
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.807FSA
18
Feb 26, 2026
4.2Energy (Wh)
18
Feb 26, 2026
86.67Accuracy (%)
17
Jun 2, 2026
46.75Overall Acc
17
Feb 26, 2026
52.4Average Score
16
Jul 8, 2026
1Average Rank
16
May 11, 2026
85.9Accuracy
14
Jun 24, 2026
46.9BFCL Score
14
Jun 19, 2026
77.9Accuracy
14
Mar 18, 2026
52.4Pass Rate
14
Feb 26, 2026
71.4Pass Rate
14
Feb 26, 2026
57.1Pass Rate
14
Feb 26, 2026
89.4Accuracy
14
Feb 26, 2026
86.85Simple Accuracy
13
May 29, 2026
75.6Accuracy
13
Feb 26, 2026
63Accuracy
12
May 26, 2026
87.06Accuracy
12
May 26, 2026
79.68Accuracy
12
May 26, 2026
87.4Overall Accuracy
12
Mar 4, 2026
94.6Overall Accuracy
12
Mar 4, 2026
77.9Overall Accuracy
12
Mar 4, 2026
94Overall Accuracy
12
Mar 4, 2026
84.5Overall Accuracy
12
Mar 4, 2026
100Success Rate (Simple, Python)
12
Feb 26, 2026
83.2ROUGE-L
12
Apr 8, 2026