Frontier Models Vary Up to 7x in Tokens Per Task, Data Shows

Artificial Analysis data shows frontier models with similar intelligence scores differ up to 7x in tokens per task, with OpenAI models burning 197k tokens per task due to verbose chain-of-thought.

2026-10-19 ~ 2026-10-20 · 2 related posts

• OpenAI models top Artificial Analysis token burn at 197k output tokens per task — teortaxesTex · 2026-10-19
• Frontier models differ 7x in tokens burned per task, AA data shows — shensi · 2026-10-20