Tool selection
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
80.8Similarity
39
May 26, 2026
97.42Accuracy
20
Feb 26, 2026
96.3Accuracy
20
Feb 26, 2026
94.04Accuracy
20
Feb 26, 2026
97.33Accuracy
20
Feb 26, 2026
99.4Tool Selection F1 (2 calls)
15
Mar 10, 2026
99.29P(Use)
14
Jun 4, 2026
36.6F1 Score
14
May 26, 2026
20.7F1 Score
12
May 13, 2026
21.1F1 Score
12
May 13, 2026
58.5F1 Score
12
May 13, 2026
100Accuracy
10
Feb 26, 2026
64.4Accuracy
10
Feb 26, 2026
24Tool Selection Accuracy
8
Mar 24, 2026
45Tool Selection Accuracy
8
Mar 24, 2026
83.4Accuracy
8
Mar 17, 2026
83R@1
7
Mar 17, 2026
39.2Recall@1
7
Mar 17, 2026
97.5Recall@1
4
Jul 8, 2026
89.87Recall@1
4
Jul 8, 2026
97.5Recall@1
4
Jul 8, 2026
67.35Recall@1
4
Jul 8, 2026
67.2Recall@1
4
Jul 8, 2026
30.64Recall@1
4
Jul 8, 2026
59.12Recall@1
4
Jul 8, 2026