‹ back to 2026-09-03

Post-Training Language Models for Gold-Medal Performance in Coding Competitions

arXiv cs.LG LLMs & Foundation Models Aleksander Ficek, Sean Narenthiran, Mehrzad Samadi, Somshubra Majumdar, Boris Ginsburg 2026-09-02

TL;DR - Researchers developed a post-training and test-time refinement pipeline that enabled Nemotron models to achieve gold-medal-level competitive programming performance. Their specialized Ultra-CC system scored 535.4/600 on IOI 2026, surpassing both the gold threshold and the top human score under equivalent competition constraints.

The pipeline combines 22,000 curated problems, synthetic reasoning traces, supervised fine-tuning, and reinforcement learning.
GenCorrect iteratively generates, evaluates, and refines diverse candidate solutions using additional test-time compute.
On IOI 2025, Nano-CC rose from 130 to 291 points after post-training and reached 468 with GenCorrect; Ultra-CC scored 502.
On IOI 2026, the competition-specific Ultra-CC system exceeded the top human score of 498.27 while observing the same time, internet-access, and submission constraints.

view merged work →