List your company

Geometric Reasoning on BBH Geometric Shapes

53AccuracyZero-shot (Default Imp.)
29.0835.2941.547.71May 29, 2026

Evaluation results

MethodLinks
Zero-shot (Default Imp.)Workflow Type=Zero-shot, LLM Model=DeepSeek-V3.12026.05530.07
Dynamic Workflow (ReAct)Workflow Type=Dynamic, LLM Model=DeepSeek-V3.12026.05352.4
Static WorkflowWorkflow Type=Static, LLM Model=DeepSeek-V3.12026.05300.63