List your company

Reasoning on Big-Bench Hard (Subtask Mean/Std Reporting)

100BBH: Boolean Expressions (Mean)PSAO.LLM
98.200898.667999.13599.6021May 14, 2026

Evaluation results

MethodLinks
PSAO.LLMModel=Gemini-2-Flash2026.05100072.731.82
COPROModel=Gemini-2-Flash2026.0598.41.0568.913.58
MIPROModel=Gemini-2-Flash2026.0598.271.2667.093.37