Igor Gitman retweeted
🎆 Nemotron-3.5-Super-VL is here! 🎆
✅ Same base architecture as Super-3.0: 120B total, 12B active plus Vision encoder
✅ Ahead of Ultra-3.0 on most benchmarks! And now with visual reasoning!
✅ SWEBench-Pro 51.79%, AA index of 26 vs 23 for Ultra-3.0
Post-training pipeline is a greatly simplified and improved version of what we had for Ultra-3.0.
We reduced number of teachers, SFT set size while significantly improving data and environments quality and made it multimodal! 1/5
🤖 Made with AI
We’re finally able to share all the assets and technical details of our Nemotron system, which achieved gold-medal-level performance at the IMO-26.
The release includes:
* Two specialized models that were part of the final ensemble system, alongside the generally available Nemotron3-Ultra checkpoint
* Two new large-scale datasets for SFT and RL to help models produce better natural-language mathematical proofs
* A set of 200 novel IMO-level mathematical problems
* A technical report with all the details needed to reproduce our work
We hope this release enables others to build on our work and helps advance open-source AI.
Everything is available at: huggingface.co/collections/n….
Igor Gitman retweeted
Congrats to our researchers for exceeding the gold medal threshold on the International Olympiad in Informatics (IOI) 2026 problem set 🥇
Our fine-tuned Nemotron model scored 535.4 out of 600, as graded by the IOI team — higher than the top-scoring human participant.
The team competed unofficially in Uzbekistan, where the International Technical Committee supervised the human contestants. The model had no internet access and faced the same time limits and submission constraints, using the same platform in parallel with the official competition.
Read more in the technical report: arxiv.org/abs/2609.02849
Igor Gitman retweeted
Nemotron 3.5 Lightning:
Same architecture as 3.0 Nano,
with added speculative decoding, and with the intelligence of 3.0 Super.
⚡️⚡️⚡️
Igor Gitman retweeted
Today we’re releasing ⚡️ Nemotron 3.5 Lightning ⚡️— our fastest open model for agentic workloads.
Built on Nemotron 3.0 Nano (30B MoE, 3B active), it got updated pre-training, mid-training, and new SFT and RLVR pipelines to approach Nemotron 3.0 Super–class accuracy.
Boosted MTP heads plus DFlash and DSpark speculative decoding deliver the throughput gains.
Igor Gitman retweeted
The biggest question facing US AI leadership is whether we will treat AI models as infrastructure.
Infrastructure (like the internet, electricity, transportation networks) is best built by lots of organizations and countries working together - in cooperation and in competition.
The US knows how to build great infrastructure. Every time we have done it, we have opened new horizons of possibility.
I believe it is inevitable that we will do the same with AI, and open models will be at the heart of this new infrastructure.
Open models are enabling companies and institutions from brand-new startups to titans of every industry to build their own future, to capitalize on their perspective and ideas to better serve customers and solve problems. Open models make sovereignty possible.
Policymakers that want to keep America AI at the forefront of this opportunity will understand how necessary open models are: they are now the critical infrastructure of the AI age.
For my first post, I’m sharing a letter @NVIDIA signed on why open models matter.
AI will transform every industry, power every company, and be built by every country.
Open models strengthen safety and cybersecurity, accelerate innovation and diffusion, and enable sovereignty.
The world needs both frontier closed models and frontier open models.
images.nvidia.com/pdf/Open-W…
Igor Gitman retweeted
For my first post, I’m sharing a letter @NVIDIA signed on why open models matter.
AI will transform every industry, power every company, and be built by every country.
Open models strengthen safety and cybersecurity, accelerate innovation and diffusion, and enable sovereignty.
The world needs both frontier closed models and frontier open models.
images.nvidia.com/pdf/Open-W…
We're happy to announce that our Nemotron-based system scored 30 out of 42 points at the International Mathematical Olympiad (IMO) 2026, held last week. The IMO team officially graded the solutions and certified that the score was equivalent to a Gold Medal for a human participant.
1/5
Congratulations to the students who competed at the International Mathematical Olympiad (IMO) 2026. 👏
We put Nemotron 3 Ultra to the test to take on the same problems in the same time limit, with no internet or external tools.
The IMO team graded its solutions 30/42, above the 29-point gold threshold. 🥇
What excites me most about this project is not the Gold Medal score itself. Other AI systems have achieved this before, and even this year, our score is not the highest. What is unique about our work that we plan to open-source the entire pipeline leading to this result. We will release the models, all of the data used to train them, the software used for training and inference, and the full recipe that anyone can use to improve their own models. I feel very happy that we are able to do this and can contribute to the open AI ecosystem.
4/5
Last year’s IMO results from OpenAI and DeepMind were an amazing achievement and very inspiring to me personally. They showed that solving extremely hard math problems with AI is within our reach.
This year, we developed a pipeline to reproduce this result with Nemotron and will share it openly to enable others to do the same.
Next year, every AI model developed by anyone will be able to earn an IMO Gold Medal.
5/5
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 huggingface.co/datasets/nvid…
Nemotron-Math-Proofs-v2: 80K solutions and verifications for hard mathematical proofs huggingface.co/datasets/nvid…
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 huggingface.co/datasets/nvid…
If you want to learn more details, check out our tech report research.nvidia.com/labs/nem…
NVIDIA Nemotron 3 Ultra is now live!
Frontier accuracy, 5X greater speed, 30% lower cost.
Deploy however you need - on-premise, on the cloud, or at the edge.
Model is live on HuggingFace under the OpenMDW 1.1 license.
youtube.com/watch?v=D8LIIvQV…
Igor Gitman retweeted
⚡ NVIDIA Nemotron 3 Super is live on OpenRouter!
120B params, 12B active. Hybrid Mamba-Transformer MoE with highest throughput efficiency in its class.
1M context. Fully open weights, data, and recipes. Built for multi-agent systems that need to think fast.
Nemotron 3 Super is out! It's really good and it will only get better from here.
And we release all the details - tech report, training code, training data, model weights. Everything you need to build a model like this yourself!
Announcing NVIDIA Nemotron 3 Super!
💚120B-12A Hybrid SSM Latent MoE, designed for Blackwell
💚36 on AAIndex v4
💚up to 2.2X faster than GPT-OSS-120B in FP4
💚Open data, open recipe, open weights
Models, Tech report, etc. here:
research.nvidia.com/labs/nem…
And yes, Ultra is coming!
Igor Gitman retweeted
Nemotron 3 Super is here — 120B total / 12B active, Hybrid SSM Latent MoE, designed for Blackwell.
Truly open: permissive license, open data, open training infra. See analysis on @ArtificialAnlys
Details in thread 🧵below:
Igor Gitman retweeted
Nemotron Super (120B, 10B active, ≈"3B" class speed) destroys all Qwens, gpt-oss, matches Kimi K2.5, exceeds Step 3.5 Flash and V3.2, and to my knowledge is only beaten by two open models (309B MiMo and Speciale) on the most interesting benchmark today.
@htihle pls test
