We released Nemotron 3 Ultra! It's quite strong across the board, but is especially good at math reasoning tasks compared to other open models. With enough TTC Ultra does really well on hard math competitions like IMO, USAMO and Putnam.

And as always, we aren't only releasing the model, but all datasets and recipes that make it this strong.

Nemotron-SFT-Math-v4: 550K solutions to "final answer" math problems with and without Python tool use https://huggingface.co/datasets/nvidia/Nemotron-SFT-Math-v4

Nemotron-Math-Proofs-v2: 80K solutions and verifications for hard mathematical proofs https://huggingface.co/datasets/nvidia/Nemotron-Math-Proofs-v2

Nemotron-RL-Math-v2: 4K selected math problems with verified final answers. This dataset is much higher quality than any previous math RL set we released https://huggingface.co/datasets/nvidia/Nemotron-RL-Math-v2

If you want to learn more details, check out our tech report https://research.nvidia.com/labs/nemotron/files/NVIDIA-Nemotron-3-Ultra-Technical-Report.pdf