Proof or Bluff? Evaluating LLMs on 2025 USA Math Olympiad

• URL: http://arxiv.org/abs/2503.21934v4
• Date: Wed, 30 Apr 2025 02:42:44 GMT
• Title: Proof or Bluff? Evaluating LLMs on 2025 USA Math Olympiad
• Authors: Ivo Petrov, Jasper Dekoninck, Lyuben Baltadzhiev, Maria Drencheva, Kristian Minchev, Mislav Balunović, Nikola Jovanović, Martin Vechev,
• Abstract summary: We evaluate state-of-the-art reasoning models on six problems from the 2025 USAMO.<n>Only Gemini-2.5-Pro achieves a non-trivial score of 25%.<n>Our results suggest that current LLMs are inadequate for rigorous mathematical reasoning tasks.
• Score: 0.8030359871216614
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent math benchmarks for large language models (LLMs) such as MathArena indicate that state-of-the-art reasoning models achieve impressive performance on mathematical competitions like AIME, with the leading model, Gemini-2.5-Pro, achieving scores comparable to top human competitors. However, these benchmarks evaluate models solely based on final numerical answers, neglecting rigorous reasoning and proof generation which are essential for real-world mathematical tasks. To address this, we introduce the first comprehensive evaluation of full-solution reasoning for challenging mathematical problems. Using expert human annotators, we evaluated several state-of-the-art reasoning models on the six problems from the 2025 USAMO within hours of their release. Our results reveal that all tested models struggled significantly: only Gemini-2.5-Pro achieves a non-trivial score of 25%, while all other models achieve less than 5%. Through detailed analysis of reasoning traces, we identify the most common failure modes and find several unwanted artifacts arising from the optimization strategies employed during model training. Overall, our results suggest that current LLMs are inadequate for rigorous mathematical reasoning tasks, highlighting the need for substantial improvements in reasoning and proof generation capabilities.

Related papers

• Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models [86.45058529521258]
  OlymMATH is a novel Olympiad-level mathematical benchmark designed to rigorously test the complex reasoning capabilities of LLMs.<n>OlymMATH features 200 meticulously curated problems, each manually verified and available in parallel English and Chinese versions.
  arXiv  Detail & Related papers  (2025-03-27T11:20:17Z)
• Large Language Models and Mathematical Reasoning Failures [1.6114012813668932]
  This paper investigates the mathematical reasoning capabilities of large language models (LLMs) using 50 newly constructed high-school-level word problems.<n>We rigorously analyze both final answers and solution steps to identify reasoning failures.<n>We find that while newer models (e.g., o3-mini, deepseek-r1) achieve higher accuracy, all models exhibit errors in spatial reasoning, strategic planning, and arithmetic.
  arXiv  Detail & Related papers  (2025-02-17T09:07:32Z)
• MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations [90.07275414500154]
  We observe significant performance drops on MATH-P-Hard across various models. We also raise concerns about a novel form of memorization where models blindly apply learned problem-solving skills.
  arXiv  Detail & Related papers  (2025-02-10T13:31:46Z)
• Explore Theory of Mind: Program-guided adversarial data generation for theory of mind reasoning [88.68573198200698]
  We introduce ExploreToM, the first framework to allow large-scale generation of diverse and challenging theory of mind data. Our approach leverages an A* search over a custom domain-specific language to produce complex story structures and novel, diverse, yet plausible scenarios. Our evaluation reveals that state-of-the-art LLMs, such as Llama-3.1-70B and GPT-4o, show accuracies as low as 0% and 9% on ExploreToM-generated data.
  arXiv  Detail & Related papers  (2024-12-12T21:29:00Z)
• UTMath: Math Evaluation with Unit Test via Reasoning-to-Coding Thoughts [7.856746367263317]
  This paper introduces the UTMath Benchmark, a robust evaluation framework designed to assess Large Language Models. It comprises 1,053 cutting-edge problems spanning nine mathematical domains, with an average of 68 test cases per problem. The best-performing model, o1-mini, solving only 32.57% of the problems, followed by o1-preview at 27.16%, and GPT-4o at 26.93%.
  arXiv  Detail & Related papers  (2024-11-11T18:59:02Z)
• Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models [63.31878920079154]
  We propose a benchmark specifically designed to assess large language models' mathematical reasoning at the Olympiad level.<n>Unlike existing Olympiad-related benchmarks, our dataset focuses exclusively on mathematics and comprises a vast collection of 4428 competition-level problems with rigorous human annotation.<n>Our experimental results show that even the most advanced models, OpenAI o1-mini and OpenAI o1-preview, struggle with highly challenging Olympiad-level problems, with 60.54% and 52.55% accuracy, highlighting significant challenges in Olympiad-level mathematical reasoning.
  arXiv  Detail & Related papers  (2024-10-10T14:39:33Z)
• Evaluating Mathematical Reasoning Beyond Accuracy [50.09931172314218]
  We introduce ReasonEval, a new methodology for evaluating the quality of reasoning steps.<n>We show that ReasonEval consistently outperforms baseline methods in the meta-evaluation datasets.<n>We observe that ReasonEval can play a significant role in data selection.
  arXiv  Detail & Related papers  (2024-04-08T17:18:04Z)
• GeoEval: Benchmark for Evaluating LLMs and Multi-Modal Models on Geometry Problem-Solving [40.46491587796371]
  We introduce the GeoEval benchmark, a comprehensive collection that includes a main subset of 2,000 problems, a 750 problems subset focusing on backward reasoning, an augmented subset of 2,000 problems, and a hard subset of 300 problems. Our evaluation of ten LLMs and MMs across these varied subsets reveals that the WizardMath model excels, achieving a 55.67% accuracy rate on the main subset but only a 6.00% accuracy on the hard subset.
  arXiv  Detail & Related papers  (2024-02-15T16:59:41Z)
• AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models [122.63704560157909]
  We introduce AGIEval, a novel benchmark designed to assess foundation model in the context of human-centric standardized exams. We evaluate several state-of-the-art foundation models, including GPT-4, ChatGPT, and Text-Davinci-003. GPT-4 surpasses average human performance on SAT, LSAT, and math competitions, attaining a 95% accuracy rate on the SAT Math test and a 92.5% accuracy on the English test of the Chinese national college entrance exam.
  arXiv  Detail & Related papers  (2023-04-13T09:39:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.