Nemotron reaches IMO gold with an open, tool-free proof pipeline
A Nemotron 3 Ultra system scored 30 of 42 points at IMO 2026, clearing the gold-medal threshold without a formal prover, external tools, or internet access. The recipe combines two specialist checkpoints trained with SFT and reinforcement learning, then uses iterative natural-language generation, verification, refinement, and selection. The team is releasing the checkpoints, data, code, solutions, and a 200-problem benchmark, making the real story reproducibility rather than a one-off score.