Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Function Calling on BFCL (Held-In)
Loading...
89.4
Accuracy
SHAD+RFT
79.9464
82.4007
84.855
87.3093
Dec 19, 2024
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
SHAD+RFT
Model=LLaMA3.1-8B
2024.12
89.4
RewardFT
Model=LLaMA3-8B
2024.12
89.3
SFT
Model=LLaMA3.1-8B
2024.12
89.3
RewardFT
Model=LLaMA3.1-8B
2024.12
88.2
SHAD+α-FT
Model=LLaMA3.1-8B
2024.12
88.2
SHAD+RFT
Model=LLaMA3-8B
2024.12
87.6
SHAD+α-FT
Model=LLaMA3-8B
2024.12
87.2
SFT
Model=LLaMA3-8B
2024.12
85.9
Rho-1
Model=LLaMA3.1-8B
2024.12
84.6
Regex+RFT
Model=LLaMA3-8B
2024.12
83.81
Rho-1
Model=LLaMA3-8B
2024.12
82.9
Regex
Model=LLaMA3.1-8B
2024.12
82.1
Regex
Model=LLaMA3-8B
2024.12
81
Regex+RFT
Model=LLaMA3.1-8B
2024.12
80.31
Feedback
Search any
task
Search any
task