An Open Recipe for IMO Gold: Training Nemotron for Olympiad Mathematics
Source
Ivan Moshkov, Stephen Ge, George Armstrong, Wei Du, Sadegh Mahdavi, Igor Gitman
Author
Ivan Moshkov, Stephen Ge, George Armstrong, Wei Du, Sadegh Mahdavi, Igor Gitman
Date
Terms in this piece · Glossary
benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
Why it matters
NVIDIA's open recipe shows a natural-language-only pipeline (no formal prover) reaching IMO gold-medal level, and releases the checkpoints, training data, and inferenceRunning a trained model to get answers — the phase where AI is actually used, as opposed to trained.Full definition → code so others can reproduce or extend it.
articleRePro: Proof-Verified Benchmark Rewriting for Reliable Evaluation of LLM Mathematical Problem SolvingXiyuan Zhou, Zhuoqi Li, Xinlei Wang, Yirui He, Yuhao Wu, Yuheng Cheng, Yan Xu, Junhua Zhao, Jinjin Gu
articleFrom Wafer-Out to First Token: Codifying Supply Chain Expertise with Nemotron and Palantir FoundryElizabeth Goodman
articleNeuro-Formal Verification: Agentic Language-Agnostic Formal Program ReasoningShuvendu K. Lahiri