An AI system has reached human level on a test for 'general intelligence'. Here's what ... - 0 views
-
Allard Strijker on 24 Dec 24Published: December 24, 2024 6.50am CET Michael Timothy Bennett, Australian National University, Elija Perrier, Stanford University A new artificial intelligence (AI) model has just achieved human-level results on a test designed to measure "general intelligence". On December 20, OpenAI's o3 system scored 85% on the ARC-AGI benchmark, well above the previous AI best score of 55% and on par with the average human score. It also scored well on a very difficult mathematics test.