Datasetpublic

bhheo/nvidia_open_reasoning_balanced_100k

nvidia_open_reasoning_balanced_100k A domain-balanced 100k reasoning SFT dataset built from three NVIDIA Open Reasoning datasets: 33,333 examples each for math, code, and science (99,999 total). Each example is a single-turn conversation with a full reasoning trace: conversations: [ {"from": "human", "value": "<problem>"}, {"from": "gpt", "value": "<think>\n<reasoning trace>\n</think><final solution>"} ] Columns column description conversations… See the full description on the dataset page: https://huggingface.co/datasets/bhheo/nvidia_open_reasoning_balanced_100k.

sourceHugging Facecc-by-4.0updated 2mo agoView on Hugging Face

0likes439downloads

Dataset Card

nvidiaopenreasoningbalanced100k

A domain-balanced 100k reasoning SFT dataset built from three NVIDIA Open Reasoning datasets: 33,333 examples each for math, code, and science (99,999 total).

Each example is a single-turn conversation with a full reasoning trace:

conversations: [
  {"from": "human", "value": "<problem>"},
  {"from": "gpt",   "value": "<think>\n<reasoning trace>\n</think><final solution>"}
]

Columns

column	description
`conversations`	human / gpt turns (gpt = `<think>...</think>` reasoning + solution)
`domain`	`math` / `code` / `science` (33,333 each)
`source`	origin dataset and subset, e.g. `nvidia/OpenMathReasoning\	aopsc6highschoololympiads`,` nvidia/OpenCodeReasoning\	codeforces`
`difficulty`	difficulty label where the origin dataset provides one (`None` otherwise)

Source datasets

This dataset is a balanced sample of the following NVIDIA datasets. All three are released under CC BY 4.0, and this dataset inherits that license.

domain	dataset	rows sampled
math	nvidia/OpenMathReasoning	33,333
code	nvidia/OpenCodeReasoning	33,333
science	nvidia/OpenScienceReasoning-2	33,333

Citation

This repository is only a convenience re-packaging. Please cite the original NVIDIA datasets, not this repository:

bibtex

@article{moshkov2025aimo2,
  title   = {AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset},
  author  = {Ivan Moshkov and Darragh Hanley and Ivan Sorokin and Shubham Toshniwal and Christof Henkel and Benedikt Schifferer and Wei Du and Igor Gitman},
  year    = {2025},
  journal = {arXiv preprint arXiv:2504.16891}
}

@article{ahmad2025opencodereasoning,
  title   = {OpenCodeReasoning: Advancing Data Distillation for Competitive Coding},
  author  = {Wasi Uddin Ahmad and Sean Narenthiran and Somshubra Majumdar and Aleksander Ficek and Siddhartha Jain and Jocelyn Huang and Vahid Noroozi and Boris Ginsburg},
  year    = {2025},
  eprint  = {2504.01943},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CL},
  url     = {https://arxiv.org/abs/2504.01943}
}

For the science subset, cite the dataset page directly:

bibtex

@misc{openscience_reasoning_2,
  title  = {OpenScienceReasoning-2},
  author = {NVIDIA},
  year   = {2025},
  howpublished = {\url{https://huggingface.co/datasets/nvidia/OpenScienceReasoning-2}}
}