Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Tool Use on API-Bank L2 cleaned (test)
Loading...
87.32
F1 (API Matching)
ToolPRM
81.2672
82.8386
84.41
85.9814
Oct 16, 2025
F1 (API Matching)
F1 (Argument Matching)
Average F1
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1 (API Matching)
F1 (Argument Matching)
Average F1
ToolPRM
Backbone=Hammer2.1-1.5...
2025.10
87.32
68.89
78.11
Hammer2.1-1.5B + Best of N
Backbone=Hammer2.1-1.5...
2025.10
86.98
68.49
77.74
Hammer2.1-1.5B + Majority
Backbone=Hammer2.1-1.5...
2025.10
85.71
68.57
77.14
Hammer2.1-1.5B
Backbone=Hammer2.1-1.5B
2025.10
85.09
67.82
76.46
Hammer2.1-1.5B + Token-level Beam Search
Backbone=Hammer2.1-1.5...
2025.10
81.5
63.84
72.67
Feedback
Search any
task
Search any
task