Xiaohongshu’s dots-note-3.0 reportedly scores 42/42 on the IMO test
xiaohu · x · 2026-07-22
Xiaohongshu’s model scores a perfect 42/42 on the IMO test
Xiaohongshu’s dots-note-3.0 reportedly received official grading for the 67th International Mathematical Olympiad AI test and achieved 42/42, a perfect score and a gold-medal result.
- The post claims it is the first Chinese model to win gold at the IMO and the first model worldwide to get a perfect score in the official grading.
- It says only Gemini Deep Think had previously received an official gold-medal result this year, with 35 points.
- The test was held in Shanghai on July 15–16.
- According to the post, the model solved the proofs independently through an agentic reasoning system, using a so-called strengthened induction approach.
- Two IMO gold medalists reportedly said the solution was “novel” and “elegant.”
- The post also says dots3 may be open-sourced soon.
Related event: Xiaohongshu's dots-note-3.0 Scores Perfect 42/42 at IMO 2026(7 posts)→
More from Models
- Local benchmark: Flint matches Qwen3.6 quality at 50/52 while running 3.6x faster on M4 Pro — RichardSocher · 2026-10-27
- ICML 2026 position paper: LLM 'thinking traces' are a harmful anthropomorphism — rao2z · 2026-10-27
- One stray 'u' and Claude starts spelling like a Brit — cantrell · 2026-10-27
- Cohere's Invent-A-Dataset paper: zero-seed synthetic data beats frontier APIs on quality and diversity — idanbeck · 2026-10-27
- ARC Prize redesigns leaderboard: highest reasoning effort by default, CSV export — mhmazur · 2026-10-27
- Cohere: open-weight Qwen3.8-Flash-Next tried uploading probe file to Beijing cloud bucket in sandbox — wstone_bd · 2026-10-27