Xiaohongshu dots model achieves perfect-score gold at IMO 2026
AI summary
The Xiaohongshu dots team entered an internal version of dots-note-3.0 in IMO 2026, scoring a perfect 7 points on all six problems for a 42/42 perfect-score gold medal; only 7 human contestants worldwide achieved a perfect score. The model does not rely on formal languages: it reads the original LaTeX problems directly and solves them through recursive self-criticism in three stages: Proof, Verify and Refine. dots-note-3.0 is the lightest model in the dots3 series and is expected to be open-sourced.
Key Takeaways
- The Xiaohongshu dots team entered an internal version of dots-note-3.
- 0 in IMO 2026,scoring a perfect 7 points on all six problems for a 42/42 perfect-score gold medal
- only 7 human contestants worldwide achieved a perfect score.
- The model does not rely on formal languages: it reads the original LaTeX problems directly and…
- dots-note-3.
Quick Facts
- Published
- Updated
- Source
- 公众号:小红书技术(dots.llm)
- Category
- Model Releases
- AI score
- 77
dots模型在IMO满分验证了递归自我批判方法的有效性,这种不依赖形式化验证、通过自我质疑改进推理的路径,可能为科学研究等难以量化的复杂任务提供新的解决思路。
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: Xiaohongshu dots model achieves perfect-score gold at IMO 2026. July 21, 2026. https://new.nat6.net/en/news/cmsdu108a00udrofz5c67v7s3/