List your company

Temporal Reasoning on BBH Date Understanding

93AccuracyDynamic Workflow (ReAct)
50.3661.4372.583.57May 29, 2026

Evaluation results

MethodLinks
Dynamic Workflow (ReAct)Workflow Type=Dynamic, LLM Model=DeepSeek-V3.12026.05930.99
Static WorkflowWorkflow Type=Static, LLM Model=DeepSeek-V3.12026.05840.28
Zero-shot (Default Imp.)Workflow Type=Zero-shot, LLM Model=DeepSeek-V3.12026.05520.1