Dots3-note open-sourced: 280B-total/16B-active multimodal model scores perfect 42/42 on IMO 2026, 1/10 the size of rivals
xiaosun86 · x · 2026-08-14
dotsstudioai has open-sourced dots3-note preview, a multimodal model with 280B total parameters and 16B active, supporting 512K context, designed for real-world long-horizon agentic tasks. SGLang provides day-0 support.
The model powered rednote's IMO 2026 gold, scoring a perfect 42/42 across all six problems, a mark achieved by only 7 human contestants this year. It did so without human formalization (Lean) or proof assistants, using only reasoning and Python end-to-end.
It is among the first models to hit 42/42 under official grading, at roughly 1/10 the size of other models that achieved this (e.g., Kimi K3, GPT5.6 Sol, Fable 5).
Related event: Xiaohongshu Open-Sources dots3-note: 280B Model for Long-Horizon Agents(8 posts)→
More from Models
- MiniMax Open-Sources Music 3.0: Generate 5-Minute Songs on 8GB VRAM — xiaohu · 2026-08-14
- Grok 4.6 Aces ARC-AGI-1, Matches GPT-5.6 at a Fraction of the Cost — elonmusk · 2026-08-14
- Zhipu Releases GLM-5.3: Post-Training Scaling Boosts Coding & Security, Open Source in Two Weeks — 智谱 · 2026-08-14
- User Speculates Claude 3 Opus is Heavily Quantized for Scale, Degrading Long-Context Performance — auto_grad_ · 2026-08-14
- AI Scores 1753 vs Human's 1000? Preference-Based Grading Critiqued for Valuing Style Over Accuracy — Spiritual_Heron_5680 · 2026-08-14
- Zhipu Crowned as China's King of Post-Training by X Users — zephyr_z9 · 2026-08-14