List your company

API Tool Use on Real-World APIs (test)

98.3TCRNaviAgent
29.03647.0186582.982Jun 24, 2025

Evaluation results

MethodLinks
NaviAgentModel=DeepSeek-V32025.0698.363.35.1135
NaviAgentModel=Qwen2.5-32B2025.0686.753.34.8427
α-UMIModel=DeepSeek-V32025.068548.36.1739
α-UMIModel=Qwen2.5-32B2025.0678.341.66.0432
α-UMIModel=Qwen2.5-14B2025.0676.731.75.827
NaviAgentModel=Qwen2.5-14B2025.066536.74.925
ReActModel=DeepSeek-V32025.065533.33.7523
ToolLLMModel=Qwen2.5-14B2025.0653.323.34.119
ToolLLMModel=DeepSeek-V32025.0653.3354.0525
ToolLLMModel=Qwen2.5-32B2025.0648.330423
ReActModel=Qwen2.5-32B2025.0635253.819
ReActModel=Qwen2.5-14B2025.0631.721.73.716