Not established from the available sources.
NVIDIA · MODEL RELEASE TRACKER
Nemotron-3-Nano-CC
A 30B-parameter specialist model derived from Nemotron 3 and fine-tuned for competitive programming. Nemotron-3-Nano-CC was trained with supervised fine-tuning and reinforcement learning and was evaluated on IOI-style benchmarks using an iterative generate-evaluate-refine inference loop.CURRENT SNAPSHOT1/5 DIMENSIONS WITH DATA
The dimensions that change the decision.
Not established from the available sources.
Not established from the available sources.
IOI performance progression and thresholdOn the IOI test, score improved from 130 before post-training to 280 after SFT and 291 after RL; with GenCorrect it reached 468 points, surpassing the gold threshold of 438.3.
Not established from the available sources.
VERIFIABLE FACTS
Every value stays attached to a source and date.
CAPABILITIES · Fine-tuning and training methodsDEVELOPER CLAIM
Received supervised fine-tuning (SFT) and reinforcement learning (RL) as post-training methods to create a specialist from Nemotron 3.
CAPABILITIES · Parameter countsDEVELOPER CLAIM
Has 30 billion total parameters and 3 billion active parameters.
CAPABILITIES · Inference strategy usedDEVELOPER CLAIM
Paired with an inference loop called GenCorrect (an iterative generate–evaluate–refine strategy) during evaluation.
BENCHMARKS · IOI performance progression and thresholdDEVELOPER CLAIM
On the IOI test, score improved from 130 before post-training to 280 after SFT and 291 after RL; with GenCorrect it reached 468 points, surpassing the gold threshold of 438.3.
LIMITATIONS · Nature of the IOI evaluationDEVELOPER CLAIM
The IOI result came from a live, prospective run under the same time, internet-access, and submission constraints as human contestants, but it was an unofficial, unsupervised benchmark and was not included in the official IOI ranking.
WHAT CHANGED