List your company

Tool Calling on Tool-Alpaca

91.17Tool Name AccuracyLlama3-70B
38.431652.123365.81579.5067May 28, 2025

Evaluation results

MethodLinks
Llama3-70BModel Series=Llama3 Series, Method=HiTEC-KTO2025.0591.1760.83
Qwen2.5-7BModel Series=Qwen2.5 Series, Method=HiTEC-KTO2025.0587.6359.19
HiTEC-KTOModel=Qwen2.5-7B2025.0587.6359.19
HiTEC-ICLModel=GPT-4-Turbo2025.0587.3561.95
HiTEC-ICLBackbone=GPT-4-Turbo2025.0587.3561.95
HiTEC-ICLModel=GPT-3.5-Turbo-01252025.0587.2758.79
VanillaBackbone=GPT-4-Turbo2025.0587.1260.75
Function CallingBackbone=GPT-4-Turbo2025.0587.1162.16
Llama3-8BModel Series=Llama3 Series, Method=HiTEC-KTO2025.0587.0252.4
HiTEC-KTOModel=Llama3-8B2025.0587.0252.4
Llama3-70BModel Series=Llama3.1 Series, Method=HiTEC-KTO2025.0586.6757.32
Llama3.1-70BModel Series=Llama3.1 Series, Method=Baseline2025.0586.0355.83
HiTEC-ICLModel=Llama3-8B2025.0585.9255.49
HiTEC-ICLBackbone=Llama3-8B2025.0585.9255.49
HiTEC-ICLBackbone=Llama3.1-8B2025.0585.9255.94
Qwen2.5-3BModel Series=Qwen2.5 Series, Method=HiTEC-KTO2025.0585.4256.08
Llama3.1-8BModel Series=Llama3.1 Series, Method=HiTEC-KTO2025.0584.1856.45
Llama3.1-8BModel Series=Llama3.1 Series, Method=Baseline2025.0584.0650.79
VanillaBackbone=Llama3.1-8B2025.0584.0650.79
Qwen2.5-1.5BModel Series=Qwen2.5 Series, Method=HiTEC-KTO2025.0582.2752.26
Hammer2-7BModel Series=Qwen2.5 Series, Method=Baseline2025.0581.7457.07
CoTBackbone=GPT-4-Turbo2025.0580.9556.46
Hammer2-1.5BModel Series=Qwen2.5 Series, Method=Baseline2025.0580.7451.88
Hammer2-3BModel Series=Qwen2.5 Series, Method=Baseline2025.0578.2353.28
Qwen2.5-0.5BModel Series=Qwen2.5 Series, Method=HiTEC-KTO2025.0573.5438.76
Hammer2-0.5BModel Series=Qwen2.5 Series, Method=Baseline2025.0564.4641.83
CoTBackbone=Llama3.1-8B2025.0563.3142.57
CoTBackbone=Llama3-8B2025.0560.5842.07
Llama3-70BModel Series=Llama3 Series, Method=Baseline2025.0549.6447.73
Llama3-8BModel Series=Llama3 Series, Method=Baseline2025.0540.4624.86
VanillaBackbone=Llama3-8B2025.0540.4624.86