List your company

Tabular Reasoning on BBH Penguins in a Table

93AccuracyZero-shot (Default Imp.)
61.869.97886.1May 29, 2026

Evaluation results

MethodLinks
Zero-shot (Default Imp.)Workflow Type=Zero-shot, LLM Model=DeepSeek-V3.12026.05930.05
Dynamic Workflow (ReAct)Workflow Type=Dynamic, LLM Model=DeepSeek-V3.12026.05720.54
Static WorkflowWorkflow Type=Static, LLM Model=DeepSeek-V3.12026.05630.21