# Hugging Face — One Model Family, Two Gold-Level Results: Fine-Tuning Nemotron for IOI and IMO

- Company: Hugging Face (huggingface.co)
- Announced: 2026-10-07T12:45:31+00:00
- Category: research-paper
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://huggingface.co/blog/nvidia/nemotron-ioi-and-imo-2026
- Record: https://forck.live/items/16378-one-model-family-two-gold-level-results-fine-tuning-nemotron-for-ioi-and-imo
- Subject: Platform
- Open weights: yes
- Models affected: Nemotron 3, Nemotron-3-Nano-CC, Nemotron-3-Ultra-CC

NVIDIA's teams fine-tuned the Nemotron 3 model family using supervised fine-tuning, reinforcement learning, and feedback-driven inference to achieve gold-medal-level performance at both the International Olympiad in Informatics (IOI) 2026 and the International Mathematical Olympiad (IMO) 2026. The IOI result was a live, prospective run under the same constraints as human contestants, while the IMO system's proofs were graded by official IMO graders. The company released open models, training datasets, benchmarks, and inference pipelines on Hugging Face.

## Evidence

Verbatim from https://huggingface.co/blog/nvidia/nemotron-ioi-and-imo-2026:

> Starting from Nemotron 3, our teams used supervised fine-tuning (SFT), reinforcement learning (RL), and feedback-driven inference to create systems that reached gold-medal level at both IMO 2026 and IOI 2026.

---

Record: https://forck.live/items/16378-one-model-family-two-gold-level-results-fine-tuning-nemotron-for-ioi-and-imo
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md