Practical AI/Brief
Nemotron specialists reach IMO gold threshold with open natural-language pipeline
Two Nemotron 3 Ultra specialist checkpoints, trained with supervised fine-tuning and reinforcement learning, scored 30 out of 42 points at IMO 2026, the gold-medal threshold. The system works entirely in natural language, with no formal prover, external tools or internet access.
BriefPublished 12 September 20261 min read1 linked source · 5 checked factsRevision 5
Starting from Nemotron 3 Ultra, the authors train two specialist checkpoints using supervised fine-tuning and reinforcement learning. An iterative search generates, verifies and refines candidate proofs, and a separate high-compute stage selects each final submission.
The system scored 30 out of 42 points at IMO 2026, reaching the gold-medal threshold, and operates entirely in natural language, with no formal prover, external tools or internet access.
The release covers the two post-trained checkpoints, the training data, the training and inference code, the submitted solutions and Nemotron-IMO-Bench, a new benchmark of 200 novel olympiad-level problems.
Our view
The open release is the practical part: checkpoints, training data, code and a 200-problem benchmark let others run and extend the same natural-language proof pipeline without a formal prover.
What the reporting says: The system scored 30 out of 42 points at IMO 2026, reaching the gold-medal threshold, and that it operates entirely in natural language with no formal prover, external tools or internet access.
