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-note-3.0 Scores Perfect 42/42 at IMO 2026(7 posts)→
More from Models
- BullshitBench update: GPT-6-Astra beats all prior OpenAI models but still trails Anthropic — scaling01 · 2026-09-11
- Astra Scores 83% on GauntletBench, First Computer-Use Agent to Beat Human Baseline — ducha_aiki · 2026-09-11
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- DeepSeek V4 Pro API to continue after Sept 2026, billing unchanged — teortaxesTex · 2026-09-11
- DeepSeek V4.1 Flash Hits 98% of GPT-6 Astra's Score at 1.4% of the Cost in Third-Party Benchmark — ayushtweetshere · 2026-09-11