List your company

Multi-step Reasoning on MUSR Objects (Accuracy, Cost)

58AccuracyStatic Workflow
34.0840.2946.552.71May 29, 2026

Evaluation results

MethodLinks
Static WorkflowWorkflow Type=Static, LLM Model=DeepSeek-V3.12026.05580.34
Dynamic Workflow (ReAct)Workflow Type=Dynamic, LLM Model=DeepSeek-V3.12026.05360.99
Zero-shot (Default Imp.)Workflow Type=Zero-shot, LLM Model=DeepSeek-V3.12026.05350.1