List your company

Tool Calling on Nexus Raven

94.84Score (Name)Llama3-70B
11.629633.232354.83576.4377May 28, 2025

Evaluation results

MethodLinks
Llama3-70BModel Series=Llama3.1 Series, Method=HiTEC-KTO2025.0594.8482.87———
Llama3.1-70BModel Series=Llama3.1 Series, Method=Baseline2025.0593.7582.72———
Llama3-70BModel Series=Llama3 Series, Method=HiTEC-KTO2025.0591.8581.92———
Qwen2.5-7BModel Series=Qwen2.5 Series, Method=HiTEC-KTO2025.0591.778.17———
Hammer2-7BModel Series=Qwen2.5 Series, Method=Baseline2025.0590.7680.96———
Llama3.1-8BModel Series=Llama3.1 Series, Method=HiTEC-KTO2025.0589.9882.28———
Hammer2-3BModel Series=Qwen2.5 Series, Method=Baseline2025.0589.1466.71———
Llama3.1-8BModel Series=Llama3.1 Series, Method=Baseline2025.0587.9372.17———
Qwen2.5-1.5BModel Series=Qwen2.5 Series, Method=HiTEC-KTO2025.0586.3764.4———
Hammer2-1.5BModel Series=Qwen2.5 Series, Method=Baseline2025.0585.8563.76———
Qwen2.5-3BModel Series=Qwen2.5 Series, Method=HiTEC-KTO2025.0583.0562.35———
Qwen2.5-0.5BModel Series=Qwen2.5 Series, Method=HiTEC-KTO2025.0582.8363.89———
Llama3-8BModel Series=Llama3 Series, Method=HiTEC-KTO2025.0578.1764.6———
Llama3-70BModel Series=Llama3 Series, Method=Baseline2025.0575.4373.25———
Hammer2-0.5BModel Series=Qwen2.5 Series, Method=Baseline2025.0564.7245.52———
Llama3-8BModel Series=Llama3 Series, Method=Baseline2025.0514.8317.44———
CoTBackbone=GPT-4-Turbo2025.05——92.1885—
CoTBackbone=Llama3-8B2025.05——64.4452.22—
CoTBackbone=Llama3.1-8B2025.05——76.7167.32—
Hammer-1.5BModel Size=1.5B2026.04————56.88
Hammer-7BModel Size=7B2026.04————74.64
HiTEC-ICLModel=GPT-4-Turbo2025.05——92.8183.15—
HiTEC-ICLModel=Llama3.1-70B2025.05——94.5483.44—
HiTEC-ICLBackbone=GPT-4-Turbo2025.05——92.8183.15—
HiTEC-ICLBackbone=Llama3-8B2025.05——82.0758.3—
HiTEC-ICLBackbone=Llama3.1-8B2025.05——87.7672.35—
HiTEC-KTOModel=Llama3.1-70B2025.05——94.8482.87—
HiTEC-KTOModel=Qwen2.5-7B2025.05——91.778.17—
Qwen2.5-1.5BModel Size=1.5B2026.04————49.88
Qwen2.5-32BModel Size=32B2026.04————82.66
Qwen2.5-7BModel Size=7B2026.04————72.83
two-step training model (AugFC)Model Size=1.5B2026.04————78.4
two-step training model (AugFC)Model Size=7B2026.04————89.01
two-step training model (AugFC)Model Size=32B2026.04————86.82
VanillaBackbone=GPT-4-Turbo2025.05——94.1382.92—
VanillaBackbone=Llama3-8B2025.05——14.8317.44—
VanillaBackbone=Llama3.1-8B2025.05——87.9372.17—
xLAM-1.3B-fcModel Size=1.5B2026.04————54.8
xLAM-2-32B-fcModel Size=32B2026.04————85.73
xLAM-7B-fcModel Size=7B2026.04————54.09