dots3-note Preview Open-Sourced: Self-Critic Model Scores Perfect IMO Gold
CodeByPoonam · x · 2026-08-31
Rednote's dots studio has released the dots3-note preview, a model that achieved a perfect gold medal at the International Math Olympiad (IMO) by learning to critique itself mid-solution.
- Specs: 280B total parameters, 16B active, 512K context, and supports text, vision, and audio.
- Core Mechanism: The model improves accuracy by recursively critiquing its own proofs during the process, rather than just generating an answer and stopping.
Related event: Rednote Open-Sources dots3-note Preview, Achieving Full Marks on IMO Test(2 posts)→
More from Models
- Z.ai Releases GLM-5.3-Flash: 320B Params, 1M Context, and NVFP4 Quantization — alejandroll10 · 2026-09-01
- Open Source Models Shift to Revenue Sharing and Licensing — zephyr_z9 · 2026-09-01
- Has anyone tuned a model to operate exclusively in E-prime yet? — cephaloform · 2026-09-01
- Heavy users report Claude quality dropping over the past week: eager to execute, no more clarifying questions — Numerous_Leopard_522 · 2026-09-01
- User seeks best LLM for CLI coding on single 3080 Ti — -samae1- · 2026-09-01
- Lan Hackathon Review: Qwen Excels in Physics/Engineering, K3 in General Intelligence — 葬AI · 2026-09-01