List your company

Tool Use on ToolBench Medium v1.0

96.3TCRNaviAgent
21.62841.01460.479.786Jun 24, 2025

Evaluation results

MethodLinks
NaviAgentModel=Deepseek-V32025.0696.348.54.45
α-UMIModel=Deepseek-V32025.0689.432.95.95
NaviAgentModel=Qwen2.5-32B2025.0681.741.54.6
α-UMIModel=Qwen2.5-32B2025.0678.8266.02
α-UMIModel=Qwen2.5-14B2025.0677.9255.88
NaviAgentModel=Qwen2.5-14B2025.0660.132.34.38
ToolLLMModel=Deepseek-V32025.0658.8303.92
ReActModel=Deepseek-V32025.0658.738.53.5
ToolLLMModel=Qwen2.5-14B2025.0653.819.74.02
ToolLLMModel=Qwen2.5-32B2025.0648.630.33.85
ReActModel=Qwen2.5-32B2025.0635.624.53.6
ReActModel=Qwen2.5-14B2025.0624.516.83.67