Tool Use
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
71SL
6
Feb 26, 2026
75.5SL Score
6
Feb 26, 2026
76.8Accuracy
6
Feb 26, 2026
57.4Success Rate
6
Feb 26, 2026
38.6Pass@1
6
Feb 26, 2026
50.7Success Rate
6
Feb 26, 2026
85.4Pass@1
6
Feb 26, 2026
2.04Hallucination Rate
6
Feb 26, 2026
5.91Hallucination Rate
6
Feb 26, 2026
0.064Hallucination Rate
6
Feb 26, 2026
5.04Tool Use Score
5
Jul 1, 2026
38Overall Score
5
Jul 1, 2026
75EM Accuracy
5
May 19, 2026
71.6Pass@1
5
May 7, 2026
87.32F1 (API Matching)
5
Apr 30, 2026
480Tokens per Turn
5
Apr 24, 2026
85.4Pass@1
5
Mar 24, 2026
75.5G1 Category SL
5
Feb 26, 2026
43Productivity
4
Jun 15, 2026
83.9Infer Time
4
Jun 11, 2026
31.3Score
4
Jun 4, 2026
88BFCL live Score
4
May 29, 2026
86.2BFCL live Score
4
May 29, 2026
71.1Tool Use Average Accuracy
4
May 22, 2026
60Success Rate
4
Apr 30, 2026