Tool Calling
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
72.7AST Soft Accuracy
49
May 15, 2026
94.99F1 Name Match
46
May 14, 2026
76.8F1 Score
42
May 15, 2026
86.73Accuracy
38
Feb 26, 2026
91.17Tool Name Accuracy
31
Feb 26, 2026
98.14Name Match Score
30
Feb 26, 2026
75.51Accuracy
27
Feb 26, 2026
90.42Name Match F1
25
Feb 26, 2026
85.3BFCL Score
18
Jun 4, 2026
65.17Overall Score
18
Mar 13, 2026
85.81Non-Live Score
18
Mar 13, 2026
68.92Overall Score
18
Mar 13, 2026
86.46Non-Live Accuracy
18
Mar 13, 2026
89ACC
17
Apr 14, 2026
82Accuracy
17
Apr 14, 2026
90.65Non-Live Success Rate
17
Mar 13, 2026
79.01Multiple Success Rate
16
May 29, 2026
96.67Multiple Success Rate
16
May 29, 2026
68.85Pass Rate
16
May 29, 2026
78.3Pass Rate
16
May 29, 2026
77.42Pass Rate
16
May 29, 2026
75.95Pass Rate
16
May 29, 2026
76.07Pass Rate
16
May 29, 2026
0.791Pass Rate
16
May 29, 2026
91.37Tool Call Name F1
16
Feb 26, 2026