Evaluating Large Language Models on the 2026 Korean CSAT Mathematics Exam: Measuring Mathematical Ability in a Zero-Data-Leakage Setting

• URL: http://arxiv.org/abs/2511.18649v2
• Date: Sun, 30 Nov 2025 15:52:16 GMT
• Title: Evaluating Large Language Models on the 2026 Korean CSAT Mathematics Exam: Measuring Mathematical Ability in a Zero-Data-Leakage Setting
• Authors: Goun Pyeon, Inbum Heo, Jeesu Jung, Taewook Hwang, Hyuk Namgoong, Hyein Seo, Yerim Han, Eunbin Kim, Hyeonseok Kang, Sangkeun Jung,
• Abstract summary: This study systematically evaluated the mathematical reasoning capabilities of Large Language Models (LLMs) using the 2026 Korean College Scholastic Ability Test (CSAT) Mathematics section.<n>To address data leakage issues in existing benchmarks, we digitized all 46 questions (22 common and 24 elective) within two hours of the exam's public release.
• Score: 5.313647446600863
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This study systematically evaluated the mathematical reasoning capabilities of Large Language Models (LLMs) using the 2026 Korean College Scholastic Ability Test (CSAT) Mathematics section, ensuring a completely contamination-free evaluation environment. To address data leakage issues in existing benchmarks, we digitized all 46 questions (22 common and 24 elective) within two hours of the exam's public release, eliminating any possibility of inclusion in model training data. We conducted comprehensive evaluations of 24 state-of-the-art LLMs across varying input modalities (Text-only, Image-only, Text+Figure) and prompt languages (Korean, English). The GPT-5 family models achieved perfect scores (100 points) under a limited set of language-modality configurations, while Grok 4, Qwen 3 235B, and Gemini 2.5 pro also scored above 97 points. Notably, gpt-oss-20B achieved 95.7 points despite its relatively small size, demonstrating high cost-effectiveness. Problem-specific analysis revealed Calculus as the weakest domain with significant performance degradation on 4-point high-difficulty problems. Text input consistently outperformed image input, while prompt language effects varied by model scale. In reasoning enhancement experiments with GPT-5 series, increased reasoning intensity improved performance (82.6->100 points) but quadrupled token usage and drastically reduced efficiency, suggesting that models with minimal reasoning may be more practical. This research contributes: (1) implementation of a completely unexposed evaluation environment, (2) a standardized digitization pipeline that converts human-targeted exam materials into LLM-ready evaluation data, and (3) a practical evaluation perspective integrating performance, cost, and time considerations. Detailed results and model comparisons are available at the 2026 Korean CSAT LLM Evaluation Leaderboard; https://isoft.cnu.ac.kr/csat2026/

Related papers

• From Abstract to Contextual: What LLMs Still Cannot Do in Mathematics [79.81905350372067]
  We study gap through contextual mathematical reasoning.<n>We introduce ContextMATH, a benchmark that repurposes AIME and MATH-500 problems into two contextual settings.<n>Open-source models decline by 13 and 34 points on SG and CS, while proprietary models drop by 13 and 20.
  arXiv  Detail & Related papers  (2026-01-30T14:56:04Z)
• RPC-Bench: A Fine-grained Benchmark for Research Paper Comprehension [65.81339691942757]
  RPC-Bench is a large-scale question-answering benchmark built from review-rebuttal exchanges of high-quality computer science papers.<n>We design a fine-grained taxonomy aligned with the scientific research flow to assess models' ability to understand and answer why, what, and how questions in scholarly contexts.
  arXiv  Detail & Related papers  (2026-01-14T11:37:00Z)
• mmJEE-Eval: A Bilingual Multimodal Benchmark for Evaluating Scientific Reasoning in Vision-Language Models [2.0467354053171243]
  We introduce textbfmmJEE-Eval, a multimodal bilingual (English and Hindi) benchmark comprising 1,460 questions from India's Chemistry Advanced examination ( 2019-2025)<n>Our evaluation of 17 state-of-the-art models reveals that while frontier VLMs (GPT-5, Gemini 2.5 Pro/Flash) achieve 77-84% accuracy on held-out 2025 questions, open-source models plateau at 37-45% despite scaling to 400B parameters.
  arXiv  Detail & Related papers  (2025-11-12T13:52:37Z)
• Large Language Models Imitate Logical Reasoning, but at what Cost? [0.42970700836450487]
  We present a study which evaluates the reasoning capability of frontier Large Language Models over an eighteen month period.<n>We measured the accuracy of three leading models from December 2023, September 2024 and June 2025 on true or false questions.<n>The improvement in performance from 2023 to 2024 can be attributed to hidden Chain of Thought prompting.
  arXiv  Detail & Related papers  (2025-09-16T04:03:42Z)
• Putnam-AXIOM: A Functional and Static Benchmark for Measuring Higher Level Mathematical Reasoning in LLMs [19.592385109516268]
  Current benchmarks for large language models (LLMs) are approaching saturation and are increasingly compromised by trainingset contamination.<n>We introduce Putnam-AXIOM, a benchmark drawn from the prestigious William Lowell Putnam Mathematical Competition.<n>The variation protocol produces an unlimited stream of equally difficult, unseen instances -- yielding contamination-resilient test bed.
  arXiv  Detail & Related papers  (2025-08-05T17:57:50Z)
• PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models [33.45006997591683]
  PHYBench is a benchmark of 500 original physics problems ranging from high school to Physics Olympiad difficulty.<n>PHYBench addresses data contamination through original content and employs a systematic curation pipeline to eliminate flawed items.<n> Evaluations show that PHYBench activates more tokens and provides stronger differentiation between reasoning models.
  arXiv  Detail & Related papers  (2025-04-22T17:53:29Z)
• 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)
• EquiBench: Benchmarking Large Language Models' Reasoning about Program Semantics via Equivalence Checking [58.15568681219339]
  We introduce EquiBench, a new benchmark for evaluating large language models (LLMs)<n>This task directly tests a model's ability to reason about program semantics.<n>We evaluate 19 state-of-the-art LLMs and find that in the most challenging categories, the best accuracies are 63.8% and 76.2%, only modestly above the 50% random baseline.
  arXiv  Detail & Related papers  (2025-02-18T02:54:25Z)
• 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.<n>It comprises 1,053 cutting-edge problems spanning nine mathematical domains, with an average of 68 test cases per problem.<n>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)
• Evaluating Research Quality with Large Language Models: An Analysis of ChatGPT's Effectiveness with Different Settings and Inputs [3.9627148816681284]
  This article assesses which ChatGPT inputs produce better quality score estimates.<n>The optimal input is the article title and abstract, with average ChatGPT scores based on these correlating at 0.67 with human scores.
  arXiv  Detail & Related papers  (2024-08-13T09:19:21Z)
• DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data [65.5290035371111]
  We introduce an approach to generate extensive Lean 4 proof data derived from high-school and undergraduate-level mathematical competition problems. We fine-tune the DeepSeekMath 7B model on this synthetic dataset, which comprises 8 million formal statements with proofs. Our model successfully proved 5 out of 148 problems in the Lean 4 Formalized International Mathematical Olympiad (FIMO) benchmark, while GPT-4 failed to prove any.
  arXiv  Detail & Related papers  (2024-05-23T09:03:42Z)
• Investigating the Limitation of CLIP Models: The Worst-Performing Categories [53.360239882501325]
  Contrastive Language-Image Pre-training (CLIP) provides a foundation model by integrating natural language into visual concepts. It is usually expected that satisfactory overall accuracy can be achieved across numerous domains through well-designed textual prompts. However, we found that their performance in the worst categories is significantly inferior to the overall performance.
  arXiv  Detail & Related papers  (2023-10-05T05:37:33Z)
• Text Classification via Large Language Models [63.1874290788797]
  We introduce Clue And Reasoning Prompting (CARP) to address complex linguistic phenomena involved in text classification. Remarkably, CARP yields new SOTA performances on 4 out of 5 widely-used text-classification benchmarks. More importantly, we find that CARP delivers impressive abilities on low-resource and domain-adaptation setups.
  arXiv  Detail & Related papers  (2023-05-15T06:24:45Z)
• Lila: A Unified Benchmark for Mathematical Reasoning [59.97570380432861]
  LILA is a unified mathematical reasoning benchmark consisting of 23 diverse tasks along four dimensions. We construct our benchmark by extending 20 datasets benchmark by collecting task instructions and solutions in the form of Python programs. We introduce BHASKARA, a general-purpose mathematical reasoning model trained on LILA.
  arXiv  Detail & Related papers  (2022-10-31T17:41:26Z)

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.