Introducing AceMath-RL-Nemotron-7B, a math reasoning model trained entirely through reinforcement learning from DeepSeek-R1-Distilled-Qwen-7B. It achieves AIME24: 69.0%, AIME25: 53.6%, and GPQA: 52.1%. Interestingly, this math-focused RL training also improves the coding

Had a lot of fun to scale up RL to improve math reasoning! Excited to introduce AceMath-RL-Nemotron-7B with a scalable training recipe 📑Full blog: research.nvidia.com/labs/adlr/acem… 🔗Model: huggingface.co/nvidia/AceMath…

Introducing AceReason-Nemotron: Advancing math and code reasoning through reinforcement learning (RL) We propose conducting RL on math-only prompts first, then on code-only prompts. Our key findings include: - Math-only RL significantly boosts both math and code benchmarks! -

with just math-RL, AceReason-Nemotron-14B surpass DeepCoder-14B on LiveCodeBench v5. we then did code-RL and found training becomes so much easier

Nvidia just dropped AceReason-Nemotron on Hugging Face Advancing Math and Code Reasoning through Reinforcement Learning

Does RL incentive reasoning capability over the starting SFT model? We show an interesting result with our recent published AceReason-Nemotron-7B model, which was trained with RL pass@K from 1 to 1024 consistently +10% on LiveCodeBench v6 perhaps scaling RL is the key

Etash Guha Ryan Marten I tried to reproduce DS-R1-distilled-7B and AceReason-7B's performance on your split (06/24-01/25), and they turn out to be 41.9 and 54.6 correspondingly, which is obviously higher than your reported number. Anything wrong here? Etash Guha Ryan Marten

📌Paper: arxiv.org/abs/2506.13284 📌Model: huggingface.co/nvidia/AceReas… 📌SFT Data: huggingface.co/datasets/nvidi… 📌Math RL Data: huggingface.co/datasets/nvidi… A series of our work on reasoning models: 📌5/22/2025: AceReason-Nemotron: Scaling RL for math and code (7B and 14B)

Introducing AceReason-Nemotron 1.1 Our previous release, AceReason-Nemotron-1.0, introduced a stage-wise RL recipe that was applied sequentially to math-only and code-only prompts, demonstrating both high efficiency and strong effectiveness. Here, we systematically investigate

With stronger SFT backbone, AceReason-Nemotron-1.1-7B significantly outperforms its predecessor and sets a record-high performance among Qwen2.5-7B-based reasoning models. 📄Report: arxiv.org/pdf/2506.13284 🤗Model: huggingface.co/nvidia/AceReas… 📚SFT Data: huggingface.co/datasets/nvidi…

The first thing we did was to make sure the eval setup is correct! We spend a lot of time to make sure our eval can - accurately reproduce the DeepSeek-R1 numbers on AIME, LiveCodeBench - it's IMPOSSIBLE to track the RL progress without a good eval set up (e.g., we see AIME up

Our released evaluation toolkit can reproduce our AceReason-Nemotron models numbers (see below): AceReason-Nemotron-1.0-7B: LiveCodeBench (Avg@8): * [05/23-05/24]: 72.0; [06/24-01/25]: 54.2 * release set v5: 51.2; release set v6: 44.4 AIME (Avg@64): * AIME'24: 68.6; AIME'25:

we have signed a deal for an additional 4.5 gigawatts of capacity with oracle as part of stargate. easy to throw around numbers, but this is a _gigantic_ infrastructure project. some progress photos from abilene:

Cable pr0n of @xAI GB200 servers at Colossus 2

Having thought about it some more, I think the 50 million H100 equivalent number in 5 years is about right. Eventually, billions.