Xiaohongshu’s dots-note-3.0 gets a perfect IMO score and becomes the world’s second gold model
量子位 · wechat · 2026-07-21
Xiaohongshu’s dots-note-3.0 scores a perfect IMO gold
According to the official IMO evaluation, Xiaohongshu’s dots-note-3.0 solved all six problems and became the first Chinese model to receive an official IMO gold-level certification, and the second model in the world to do so after Google Gemini.
- The model achieved 42/42, a perfect score.
- It reportedly solved the problems using natural language end to end, from reading the prompt to writing the proof.
- Judges said some of its solutions were elegant and even used nonstandard but correct proof strategies.
- The article argues that IMO is a stronger test than ordinary benchmarks because the problems are new, hidden before the contest, and graded under the real competition rules.
- The model used an agentic setup with natural language plus Python execution and self-critique.
The result is being framed as a major signal that Xiaohongshu has real foundation-model capabilities, and the model is expected to be open-sourced soon.
Related event: Xiaohongshu's dots-note3.0 Wins IMO Gold with Perfect Score(2 posts)→
More from Models
- Poolside’s Laguna S 2.1 gets a two-week free run on Nous Portal — NousResearch · 2026-07-22
- Qwen3.8 Max Preview looks substantially better in a side-by-side test with Kimi K3 — curiousily_ · 2026-07-22
- Moonshot’s Kimi K3 reaches #5 on MathArena as the top open model — xeophon · 2026-07-22
- Google launches Gemini 3.5 Flash Cyber for CodeMender, with limited access for governments — GoogleAI · 2026-07-22
- Gemini 3.5 Flash-Lite beats 3.1 Flash-Lite on long-context retrieval in MRCRv2 — Dillonu · 2026-07-22
- Kimi K3 tops Gemini 3.6 Flash on four shared public benchmarks — ChrisGPT · 2026-07-22