GDPval-AA is Artificial Analysis’ independent run of OpenAI’s GDPval tasks, giving models shell and web access and ranking them by Elo. In this corpus it is the leaderboard on which Opus 4.6 beat GPT-5.2 and then Sonnet 4.6 beat Opus 4.6 at 1633 Elo twelve days later.
Benchmark
GDPval-AA
Artificial Analysis' agentic evaluation framework built on OpenAI's GDPval dataset of real-world tasks across 44 occupations, scored as an Elo leaderboard.
Sources
Attribution and reporting linked by this record; links do not imply independent verification.
- Welcome to February 18, 2026 (theinnermostloop.substack.com)
Development timeline
Newest reporting dates first. Reporting dates may differ from event dates.
Cite or correct this record
Suggest a correction — opens a GitHub draft for you to review and submit.