#ai-evaluation

OpenAI announced a new Learning Outcomes Measurement Suite focused on causal, evidence-based evaluation of AI in classrooms. The company says independent pilots in 2026 will span seven countries, more than 10,000 students, and 10 partner institutions.

Opper tested 53 leading LLMs with a deceptively simple logic question about whether to walk or drive to a car wash 50 meters away. Only 11 models answered correctly — the car must be driven to the car wash.