Dataset Viewer
Auto-converted to Parquet Duplicate
difficulty
stringclasses
30 values
source
stringclasses
16 values
domain
stringclasses
3 values
conversations
listlengths
2
2
null
nvidia/OpenMathReasoning|aops_c6_high_school_olympiads
math
[ { "from": "human", "value": "Let \\(a, b, c\\) be reals satisfying \\(a^2 + b^2 + c^2 = 6\\). Calculate the maximum value of the expression \\((a-b)^3 + (b-c)(c-a)\\)." }, { "from": "gpt", "value": "<think>\nOkay, so I have this problem where I need to find the maximum value of the expression (a...
null
nvidia/OpenScienceReasoning-2
science
[ { "from": "human", "value": "Solve the following problem. Make sure to put the answer (and only answer) inside \\boxed{}.\n\nWhich of the following scheduling algorithms could potentially lead to starvation in a computer system?\nA: First-Come, First-Served (FCFS)\nB: Shortest Job First (SJF)\nC: Round Robi...
null
nvidia/OpenMathReasoning|aops_c6_high_school_olympiads
math
[ { "from": "human", "value": "Let \\( G \\) be a simple graph on \\( n \\) vertices (\\( n > 3 \\)) with no vertex of degree \\( n-1 \\). Suppose that for any two vertices of \\( G \\), there is a unique vertex joined to both of them. Calculate the common degree of each vertex in \\( G \\)." }, { "fr...
null
nvidia/OpenMathReasoning|aops_c6_high_school_olympiads
math
[ { "from": "human", "value": "Find all integers $(x, y, z)$ satisfying the equation $12^x + y^4 = 56^z$." }, { "from": "gpt", "value": "<think>\nOkay, so I need to find all integer solutions (x, y, z) to the equation 12^x + y^4 = 56^z. Hmm, let's start by understanding the problem. All variables ...
UNKNOWN_DIFFICULTY
nvidia/OpenCodeReasoning|aizu
code
[ { "from": "human", "value": "You survived several months of exam wars and were able to enter ICPC University on a sunny day. On the day of admission, there was an enthusiastic recruitment of circles on the campus of the university, and you received a large number of pamphlets and returned. When you return t...
null
nvidia/OpenMathReasoning|aops_c6_high_school_olympiads
math
[ { "from": "human", "value": "In a convex quadrilateral \\(ABCD\\) with diagonals intersecting at point \\(S\\), given that \\(\\angle SAB = \\angle SBC = 30^\\circ\\) and \\(\\angle SCD = \\angle SDA = 45^\\circ\\), find the angle between the diagonals of the quadrilateral." }, { "from": "gpt", ...
null
nvidia/OpenScienceReasoning-2
science
[ { "from": "human", "value": "Solve the following problem. Make sure to put the answer (and only answer) inside \\boxed{}.\n\nLet \\( A = \\{1, 2, 3\\} \\) and \\( B = \\{a, b, c, d\\} \\). Consider the Cartesian product \\( A \\times B \\). How many subsets of \\( A \\times B \\) contain exactly one element...
null
nvidia/OpenScienceReasoning-2
science
[{"from":"human","value":"Solve the following problem. Make sure to put the answer (and only answer)(...TRUNCATED)
null
nvidia/OpenScienceReasoning-2
science
[{"from":"human","value":"Solve the following problem. Make sure to put the answer (and only answer)(...TRUNCATED)
null
nvidia/OpenScienceReasoning-2
science
[{"from":"human","value":"Solve the following problem. Make sure to put the answer (and only answer)(...TRUNCATED)
End of preview. Expand in Data Studio

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 human / gpt turns (gpt = <think>...</think> reasoning + solution)
domain math / code / science (33,333 each)
source origin dataset and subset, e.g. nvidia/OpenMathReasoning|aops_c6_high_school_olympiads, 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:

@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:

@misc{openscience_reasoning_2,
  title  = {OpenScienceReasoning-2},
  author = {NVIDIA},
  year   = {2025},
  howpublished = {\url{https://huggingface.co/datasets/nvidia/OpenScienceReasoning-2}}
}
Downloads last month
21

Papers for bhheo/nvidia_open_reasoning_balanced_100k