OSU-NLP-Group/LLM-IOAA

Code and data for the paper "Large Language Models Achieve Gold Medal Performance at the International Olympiad on Astronomy & Astrophysics (IOAA)" (https://arxiv.org/abs/2510.05016).

28
/ 100
Experimental

This project helps researchers and educators analyze how advanced AI models perform on complex astronomy and astrophysics problems. You provide a set of exam problems, and the system uses large language models to generate detailed solutions. The output consists of these solutions formatted as TeX files, which can then be compiled into PDFs for easy review and comparison. It is intended for those studying AI's capabilities in STEM education or competitive academic environments.

No commits in the last 6 months.

Use this if you want to automatically generate and evaluate solutions to astronomy and astrophysics problems using powerful AI models like GPT-5 or Claude.

Not ideal if you are looking for a general-purpose problem solver for all STEM fields, or if you need to solve problems without access to commercial large language model APIs.

astrophysics education STEM AI evaluation olympiad problem solving academic benchmarking computational astronomy
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 15 / 25
Community 5 / 25

How are scores calculated?

Stars

17

Forks

1

Language

TeX

License

MIT

Last pushed

Oct 07, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/OSU-NLP-Group/LLM-IOAA"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.