METR releases November 2026 capability measurement update: AI R&D-related capabilities double roughly every 3.6 months and are increasingly hard to measure
AI summary
METR released a capability evaluation update covering Opus 5.5 and GPT-6 Astra, finding that on TH1.1 and TH2 tasks model time horizons double roughly every 3.6 months, while the verifiable subset shows a doubling time of about 1.65 months.
Key Takeaways
- METR released a capability evaluation update covering Opus 5.
- 5 and GPT-6 Astra,finding that on TH1.
- 1 and TH2 tasks model time horizons double roughly every 3.
- 6 months,while the verifiable subset shows a doubling time of about 1.
- 65 months.
Quick Facts
- Published
- Updated
- Source
- METR:Research(网页)
- Category
- Papers & Research
- AI score
- 82
METR 用自家任务套件量化模型能力增速与短板,并讨论评测环境与 RL 训练环境趋同带来的测量偏差,方法细节可供评测设计参考。
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: METR releases November 2026 capability measurement update: AI R&D-related capabilities double roughly every 3.6 months and are increasingly hard to measure. November 20, 2026. https://new.nat6.net/en/news/sn8qb9u8fqka3mpnmy0r1nz4b/