NVIDIA Open Recipe for IMO Gold with Natural-Language Nemotron Pipeline

NVIDIA

Research official 1 src. ~1 min

Starting from Nemotron 3 Ultra, NVIDIA SFT+RL-trained two math-specialist checkpoints and ran a three-checkpoint iterative generate-verify-refine loop entirely in natural language — no formal prover, tools, or internet — scoring 30/42 at IMO 2026, above the gold threshold. Checkpoints, data, code, submitted solutions, and a 200-problem benchmark are all released.

Why it matters

First fully open recipe (weights, data, code, solutions) reaching IMO gold without formal verifiers

Importance: 4/5

First fully open recipe reaching IMO gold without formal verifiers

reasoning mathematics rl test-time-compute open-source

Sources

official An Open Recipe for IMO Gold: Training Nemotron for Olympiad Mathematics