Our new X account is live! Follow @wizwand_team for updates

Tool Calling on Nexus Raven

94.84Score (Name)

Llama3-70B

Updated 4d ago

Evaluation Results

Method	Links
Llama3-70B 2025.05		94.84	82.87	-	-
Llama3.1-70B 2025.05		93.75	82.72	-	-
Llama3-70B 2025.05		91.85	81.92	-	-
Qwen2.5-7B 2025.05		91.7	78.17	-	-
Hammer2-7B 2025.05		90.76	80.96	-	-
Llama3.1-8B 2025.05		89.98	82.28	-	-
Hammer2-3B 2025.05		89.14	66.71	-	-
Llama3.1-8B 2025.05		87.93	72.17	-	-
Qwen2.5-1.5B 2025.05		86.37	64.4	-	-
Hammer2-1.5B 2025.05		85.85	63.76	-	-
Qwen2.5-3B 2025.05		83.05	62.35	-	-
Qwen2.5-0.5B 2025.05		82.83	63.89	-	-
Llama3-8B 2025.05		78.17	64.6	-	-
Llama3-70B 2025.05		75.43	73.25	-	-
Hammer2-0.5B 2025.05		64.72	45.52	-	-
Llama3-8B 2025.05		14.83	17.44	-	-
HiTEC-ICL 2025.05		-	-	92.81	83.15
HiTEC-ICL 2025.05		-	-	94.54	83.44
HiTEC-KTO 2025.05		-	-	94.84	82.87
HiTEC-KTO 2025.05		-	-	91.7	78.17
Vanilla 2025.05		-	-	94.13	82.92
CoT 2025.05		-	-	92.18	85
HiTEC-ICL 2025.05		-	-	92.81	83.15
Vanilla 2025.05		-	-	14.83	17.44
CoT 2025.05		-	-	64.44	52.22
HiTEC-ICL 2025.05		-	-	82.07	58.3
Vanilla 2025.05		-	-	87.93	72.17
CoT 2025.05		-	-	76.71	67.32
HiTEC-ICL 2025.05		-	-	87.76	72.35