Share your thoughts, 1 month free Claude Pro on usSee more

Tool Calling on Tool-Alpaca

91.17Tool Name Accuracy

Llama3-70B

Updated 1mo ago

Evaluation Results

Method	Links
Llama3-70B 2025.05		91.17	60.83
Qwen2.5-7B 2025.05		87.63	59.19
HiTEC-KTO 2025.05		87.63	59.19
HiTEC-ICL 2025.05		87.35	61.95
HiTEC-ICL 2025.05		87.35	61.95
HiTEC-ICL 2025.05		87.27	58.79
Vanilla 2025.05		87.12	60.75
Function Calling 2025.05		87.11	62.16
Llama3-8B 2025.05		87.02	52.4
HiTEC-KTO 2025.05		87.02	52.4
Llama3-70B 2025.05		86.67	57.32
Llama3.1-70B 2025.05		86.03	55.83
HiTEC-ICL 2025.05		85.92	55.49
HiTEC-ICL 2025.05		85.92	55.49
HiTEC-ICL 2025.05		85.92	55.94
Qwen2.5-3B 2025.05		85.42	56.08
Llama3.1-8B 2025.05		84.18	56.45
Llama3.1-8B 2025.05		84.06	50.79
Vanilla 2025.05		84.06	50.79
Qwen2.5-1.5B 2025.05		82.27	52.26
Hammer2-7B 2025.05		81.74	57.07
CoT 2025.05		80.95	56.46
Hammer2-1.5B 2025.05		80.74	51.88
Hammer2-3B 2025.05		78.23	53.28
Qwen2.5-0.5B 2025.05		73.54	38.76
Hammer2-0.5B 2025.05		64.46	41.83
CoT 2025.05		63.31	42.57
CoT 2025.05		60.58	42.07
Llama3-70B 2025.05		49.64	47.73
Llama3-8B 2025.05		40.46	24.86
Vanilla 2025.05		40.46	24.86