Papers & Research

Dan Hendrycks releases new benchmarks, calls Gemini 3 the biggest long-term leap

Original title:Just how significant is the jump with Gemini 3?

AI summary

AI researcher Dan Hendrycks announced on X the release of two new benchmarks, the Text Capability Index and the Vision Capability Index, to track AI model progress. The charts show Gemini 3 Pro leading significantly on both metrics, scoring 46.5 on text capability and about 57 on vision capability; the author called its performance jump the biggest long-term leap. The leaderboard covers 7 models, including GPT-5.1, Sonnet 4.5 and GroK 4.

Key Takeaways

  • AI researcher Dan Hendrycks announced on X the release of two new benchmarks,the Text Capability…
  • The charts show Gemini 3 Pro leading significantly on both metrics,scoring 46.
  • 5 on text capability and about 57 on vision capability
  • the author called its performance jump the biggest long-term leap.
  • The leaderboard covers 7 models,including GPT-5.

Quick Facts

Published
Updated
Source
X:Dan Hendrycks (@hendrycks)
Category
Papers & Research
AI score
85
Read the original Read the full article at the original source
Why it matters

该基准由知名 AI 安全研究者主导,具有较高公信力;首次系统性量化对比多模型在推理、编码、视觉等核心能力上的表现,尤其凸显 Gemini 3 Pro 的突破性进步,为公众和行业提供了权威参考依据,值得关注。

Related entities

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.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: Dan Hendrycks releases new benchmarks, calls Gemini 3 the biggest long-term leap. November 20, 2025. https://new.nat6.net/en/news/bre39dgdb0kgep7xdsj1ibiby/

View all →