K2 Horizon open-sources six model scales; 0.9B posts 48.5 on AIME 2026
kimmonismus · x · 2026-09-09
The author highlights K2 Horizon's release as setting a useful standard for open models: six scales sharing one stack, with a far richer paper trail than most launches—enough for researchers to reproduce, audit, and modify the model rather than just download a final checkpoint. The smallest 0.9B model is already live on Hugging Face, with IFM reporting an AIME 2026 score of 48.5—not a substitute for independent testing, but a concrete target the community can verify.
More from Models
- OpenAI says agent swarm solved the Navier-Stokes Millennium Prize Problem — burny_tech · 2026-09-09
- OpenAI reveals internal AI model significantly more capable than GPT-6 Astra — Polymarket · 2026-09-09
- Labs are 'insane' to sit on trained models for months, argues researcher — Darpinian · 2026-09-09
- Rumor: Anthropic resetting usage limits daily for next 10 days — eigenron · 2026-09-09
- Solving a Millennium Prize Problem by typing 'continue' in Codex would be OpenAI's best ad — eigenron · 2026-09-09
- Astra 'suddenly different' overnight, users fume over silent model swaps and nerfs — natesiggard · 2026-09-09