The issue’s framing result. The cost ratio, not the win rate, is what it treats as the news.
Development
GPT-5.2 Thinking beats human experts on GDPval
Claim
OpenAI's GPT-5.2 Thinking outperformed human professionals on 70% of GDPval tasks across 44 occupations, at under 1% of their cost.
Reported metric: 70% of tasks, <1% of cost
Reporting date: (not necessarily the event date)
Sources
Attribution and reporting linked by this record; links do not imply independent verification.
- Welcome to December 12, 2025 (theinnermostloop.substack.com)
Cite or correct this record
Suggest a correction — opens a GitHub draft for you to review and submit.