DOoM: Difficult Olympiads of Math

Ilya Kuleshov, Ilin Pavel, Nikolay Kompanets, Ksenia Sycheva, Aleksandr Nikolich
9/27/2025
cs.AI

No confident code implementation found for this paper.

Abstract

This paper introduces DOoM, a new open-source benchmark designed to assess the capabilities of language models in solving mathematics and physics problems in Russian. The benchmark includes problems of varying difficulty, ranging from school-level tasks to university Olympiad and entrance exam questions. In this paper we discuss the motivation behind its creation, describe dataset's structure and evaluation methodology, and present initial results from testing various models. Analysis of the results shows a correlation between model performance and the number of tokens used, and highlights differences in performance between mathematics and physics tasks.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning

89% match2025

RealMath: A Continuous Benchmark for Evaluating Language Models on Research-Level Mathematics

88% match1 repo202025

SymPyBench: A Dynamic Benchmark for Scientific Reasoning with Executable Python Code

86% match2025

Towards a Large Physics Benchmark

85% match2025

CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science Mastery

85% match1 repo462024

EngiBench: A Benchmark for Evaluating Large Language Models on Engineering Problem Solving

85% match2025

Cite this paper

@article{kuleshov2025doom,
  title  = {DOoM: Difficult Olympiads of Math},
  author = {Ilya Kuleshov and Ilin Pavel and Nikolay Kompanets and Ksenia Sycheva and Aleksandr Nikolich},
  year   = {2025},
  eprint = {2509.23529},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2509.23529v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2509.23529.svg)](https://codeofpaper.com/paper/2509.23529)

Discussion