2 datasets found
  1. h

    Data from: mgsm

    • huggingface.co
    • opendatalab.com
    Updated Jun 12, 2024
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    Julen Etxaniz (2024). mgsm [Dataset]. https://huggingface.co/datasets/juletxara/mgsm
    Explore at:
    CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
    Dataset updated
    Jun 12, 2024
    Authors
    Julen Etxaniz
    License

    Attribution-ShareAlike 4.0 (CC BY-SA 4.0)https://creativecommons.org/licenses/by-sa/4.0/
    License information was derived automatically

    Description

    Multilingual Grade School Math Benchmark (MGSM) is a benchmark of grade-school math problems, proposed in the paper Language models are multilingual chain-of-thought reasoners.

    The same 250 problems from GSM8K are each translated via human annotators in 10 languages. The 10 languages are: - Spanish - French - German - Russian - Chinese - Japanese - Thai - Swahili - Bengali - Telugu

    You can find the input and targets for each of the ten languages (and English) as .tsv files. We also include few-shot exemplars that are also manually translated from each language in exemplars.py.

  2. h

    BenchMAX_Math

    • huggingface.co
    Updated Feb 11, 2025
    Share
    FacebookFacebook
    TwitterTwitter
    Email
    Click to copy link
    Link copied
    Close
    Cite
    LLaMAX (2025). BenchMAX_Math [Dataset]. https://huggingface.co/datasets/LLaMAX/BenchMAX_Math
    Explore at:
    Dataset updated
    Feb 11, 2025
    Authors
    LLaMAX
    License

    Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
    License information was derived automatically

    Description

    Dataset Sources

    Paper: BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models Link: https://huggingface.co/papers/2502.07346 Repository: https://github.com/CONE-MT/BenchMAX

      Dataset Description

    BenchMAX_Math is a dataset of BenchMAX, sourcing from MGSM, which evaluates the math reasoning capability in multilingual scenarios. We extend the original MGSM dataset by six additional languages, i.e. Arabic, Czech, Hungarian, Korean, Serbian, and… See the full description on the dataset page: https://huggingface.co/datasets/LLaMAX/BenchMAX_Math.

  3. Not seeing a result you expected?
    Learn how you can add new datasets to our index.

Share
FacebookFacebook
TwitterTwitter
Email
Click to copy link
Link copied
Close
Cite
Julen Etxaniz (2024). mgsm [Dataset]. https://huggingface.co/datasets/juletxara/mgsm

Data from: mgsm

juletxara/mgsm

Multilingual Grade School Math Benchmark (MGSM)

Related Article
Explore at:
2 scholarly articles cite this dataset (View in Google Scholar)
CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.
Dataset updated
Jun 12, 2024
Authors
Julen Etxaniz
License

Attribution-ShareAlike 4.0 (CC BY-SA 4.0)https://creativecommons.org/licenses/by-sa/4.0/
License information was derived automatically

Description

Multilingual Grade School Math Benchmark (MGSM) is a benchmark of grade-school math problems, proposed in the paper Language models are multilingual chain-of-thought reasoners.

The same 250 problems from GSM8K are each translated via human annotators in 10 languages. The 10 languages are: - Spanish - French - German - Russian - Chinese - Japanese - Thai - Swahili - Bengali - Telugu

You can find the input and targets for each of the ten languages (and English) as .tsv files. We also include few-shot exemplars that are also manually translated from each language in exemplars.py.

Search
Clear search
Close search
Google apps
Main menu