{
  "id": 20864515,
  "title": "It takes only minutes for AI tool to ace all English, math CSAT questions",
  "url": "https://urgent.news/2026/11/20/it-takes-only-minutes-for-ai-tool-to-ace-all-english-math-csat",
  "topic": "ai",
  "section": "AI",
  "published": "2026-11-20T06:47:02.000Z",
  "source": {
    "name": "The Korea Times",
    "slug": "the-korea-times-koreatimes",
    "url": "https://www.koreatimes.co.kr/southkorea/education/20261120/it-takes-only-minutes-for-ai-tool-to-ace-all-english-math-csat-questions"
  },
  "original_language": "en",
  "account": "In a remarkable display of artificial intelligence capabilities, a paid version of the Claude model was able to flawlessly answer every English reading and mathematics question in a College Scholastic Ability Test (CSAT) exam in a mere minutes. This achievement, conducted during a reporter-run test, starkly contrasted with the performance of free AI tools like Perplexity and ChatGPT. Perplexity demonstrated an impressive accuracy of 71 out of 74 correct answers, committing only one noticeable error and leaving two graphic-based questions unanswered. ChatGPT, on the other hand, excelled in English reading, answering all such questions correctly, yet faltered in mathematics, correctly answering just 32 out of 46 questions, with two incorrect and twelve unconfirmed responses. All models were evaluated using the 2027 academic year university entrance exam papers, with their answers verified against official answer keys provided by the state-run Korea Institute for Curriculum and Evaluation. The CSAT test encompassed all 28 English reading questions, excluding the listening section, and 46 mathematics questions from the common section and three electives. Claude's Opus 5.5 model, operating on a \"High\" effort level, managed to accurately solve all 74 English and mathematics questions, marking a significant milestone in the potential of AI technology.",
  "summary": "A paid Claude model answered every English reading and mathematics question correctly in a reporter-run test of the College Scholastic Ability Test (CSAT), completing in minutes a set of problems that students spend many years preparing to solve. Even the free versions of artificial intelligence (AI) tools delivered impressive results. Perplexity answered 71 of the 74 questions correctly, making…",
  "key_points": [
    "Claude AI flawlessly answers all CSAT English and math questions in minutes",
    "Perplexity AI corrects 71 out of 74 CSAT answers, misses two graphic questions",
    "ChatGPT excels in English, struggles with math in CSAT test"
  ],
  "editors_take": "Claude's perfect score on complex entrance exam questions signals a widening performance gap between premium high-effort models and free AI tools in high-stakes academic reasoning tasks.",
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}