One Model Family, Two Gold-Level Results: Fine-Tuning Nemotron for IOI and IMO
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.
ProofVendor claim only
Key points
- Our recent results show that Nemotron is a strong, adaptable foundation for building world-class specialist models.
- Start with a strong Nemotron base model.
- Curate domain-specific problems and high-quality reasoning traces.
- Nemotron-3-Nano-CC, with 30 billion total parameters and 3 billion active parameters, received both SFT and RL.
Sources (1)
- [1]One Model Family, Two Gold-Level Results: Fine-Tuning Nemotron for IOI and IMOHugging Face Blog · Oct 7, 12:45 PM
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.
Our recent results show that Nemotron is a strong, adaptable foundation for building world-class specialist models.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 1, 2026Introducing Clef: our open-source decision models, and new RL fine-tuning platform
- Oct 1, 2026Fine-Tuning NVIDIA Nemotron for Saudi Arabic Dialects, with a Path to Other Languages
- Sep 30, 2026huggingface/transformers v5.18.0: Release 5.18.0
- Sep 28, 2026Notes on NVIDIA Nemotron
- Sep 19, 2026ollama/ollama v0.34.3
- Jul 15, 2026huggingface/transformers v5.14.0: Release v5.14.0
