Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Function Calling on Seal-Tools
Loading...
94.94
F1 Score
two-step training model (AugFC)
74.1088
79.5169
84.925
90.3331
Apr 7, 2026
F1 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1 Score
two-step training model (AugFC)
Model Size=32B
2026.04
94.94
two-step training model (AugFC)
Model Size=7B
2026.04
94.92
Qwen2.5-32B
Model Size=32B
2026.04
93.39
xLAM-2-32B-fc
Model Size=32B
2026.04
90.49
Hammer-7B
Model Size=7B
2026.04
89.87
two-step training model (AugFC)
Model Size=1.5B
2026.04
88.98
Hammer-1.5B
Model Size=1.5B
2026.04
88.65
Qwen2.5-7B
Model Size=7B
2026.04
80.83
xLAM-1.3B-fc
Model Size=1.5B
2026.04
80.43
xLAM-7B-fc
Model Size=7B
2026.04
76.87
Qwen2.5-1.5B
Model Size=1.5B
2026.04
74.91
Feedback
Search any
task
Search any
task