Xiaohongshu's dots-note3.0 Scores Perfect 42/42 at IMO 2026 with End-to-End Proofs

小红书技术REDtech · wechat · 2026-07-21

The dots team from Xiaohongshu announced that its internal model, dots-note3.0, participated in the 67th International Mathematical Olympiad (IMO 2026) and won a gold medal with a perfect score (42/42), a feat achieved by only 7 human contestants globally.

Technical Highlights: Unlike traditional approaches relying on translating problems into formal languages like Lean, dots-note3.0 directly reads raw LaTeX problems and operates end-to-end in an Agentic manner, combining natural language reasoning with Python code execution.

Core Mechanism: The model emphasizes "recursive self-critique," utilizing a continuous loop of Proof, Verify, and Refine to conduct multi-round parallel reasoning and self-correction. The team noted that dots-note3.0 is the lightest version in the upcoming dots3 series, which is expected to be open-sourced to the community.

Related event: Xiaohongshu's dots-note3.0 Wins IMO Gold with Perfect Score(2 posts)→

Original post →

More from Models

Models channel →