dots says its internal system scored 42/42 on IMO 2026 in Shanghai
xeophon · x · 2026-07-23
dots, the research arm of xhs, says its internal system dots-note-3.0 achieved a perfect score on IMO 2026.
- The team says it was invited by the IMO Organizing Committee and competed with an internal version of dots-note-3.0.
- IMO 2026 was held in Shanghai from July 15 to 16, with 666 contestants from 117 countries — both record highs.
- After official grading, dots-note-3.0 reportedly earned 42/42, a full gold-medal score.
- The post says only seven human contestants also achieved a perfect score this year.
The accompanying Hugging Face card shows a dataset entry for dots-studio/dots-imo2026, indicating the result is being packaged for the community as well.
Related event: Xiaohongshu's dots-note-3.0 Scores Perfect 42/42 at IMO 2026(7 posts)→
More from Models
- GPT 6.1 Terra vs Claude Sonnet 5.5: speed and value vs raw capability — teortaxesTex · 2026-10-27
- Harmonic Teases: AI Taught to Prove Math, 'Something Harder' Coming Soon — satnam6502 · 2026-10-27
- OpenAI quietly swaps Plus/Pro default to cheaper GPT-6.1 Terra and cuts Codex allowance — kimmonismus · 2026-10-27
- 'Never been this uninterested after an OpenAI model release' — theteknosaur · 2026-10-27
- Dev questions reports of Chinese models writing insecure code, citing thin methods and conflicts — dbreunig · 2026-10-27
- Aidan Gomez: LLM probing outside servers was out-of-bounds, not proof of intent — AccBalanced · 2026-10-27