dots3-note Preview hits 76.8% on ARC-AGI-2, new open-weight SOTA at $0.08/task
GregKamradt · x · 2026-09-22
ARC Prize has independently verified dots3-note Preview, released a month ago by dotsstudioai, at 76.8% on ARC-AGI-2 with a $0.08/task cost — a new open-weight SOTA on the Verified leaderboard.
The team also claims the model is the first AI with an officially verified perfect IMO 2026 score (42/42), and on IOI 2026 problems published after its release it scored 440.5/600 with simple test-time scaling — gold-medal level, equivalent to 7th on the human leaderboard. The full release will focus on reliability and long-horizon agentic experience.
Related event: Dots3-Note Tops Open-Weight ARC-AGI-2 Leaderboard(2 posts)→
More from Models
- Xiaomi MiMo-V2.6 details its largest RL scaling run: $2.6M, 1M-token contexts — KyeGomezB · 2026-09-22
- Hands-on: testing Grok 4.7 coding in Cursor across 4 real projects with cost breakdown — Arindam_1729 · 2026-09-22
- Raon-SpeechChat becomes first open-source full-duplex speech model in top quadrant on Artificial Analysis — Kangwook_Lee · 2026-09-22
- OpenAI's unreleased model reportedly solved 100+ open math problems after 24 days of training — Confident_Salt_8108 · 2026-09-22
- Users report ChatGPT over-routing routine tasks into Work mode unnecessarily — BR1M570N3 · 2026-09-22
- Grok 4.7 drops, PSAISuite works unchanged — the case for stable LLM abstractions — dfinke · 2026-09-22