OpenAI’s o3 AI model scores lower on a benchmark than the company initially implied

  • staffstaff
  • AI
  • April 20, 2025
  • 0 Comments

A discrepancy between first- and third-party benchmark results for OpenAI’s o3 AI model is raising questions about the company’s transparency and model testing practices. When OpenAI unveiled o3 in December, the company claimed the model could answer just over a fourth of questions on FrontierMath, a challenging set of math problems. That score blew the […]

  • Related Posts

    Anduril is working on the difficult AI-related task of real-time edge computing

    Anduril announced its ninth acquisition on Monday with the purchase of Dublin’s Klas, makers of ruggedized edge computing equipment for the military and first responders. Anduril wouldn’t reveal financial details…

    Continue reading
    People struggle to get useful health advice from chatbots, study finds

    With long waiting lists and rising costs in overburdened healthcare systems, many people are turning to AI-powered chatbots like ChatGPT for medical self-diagnosis. About 1 in 6 American adults already…

    Continue reading

    Leave a Reply

    Your email address will not be published. Required fields are marked *

    You Missed

    Anduril is working on the difficult AI-related task of real-time edge computing

    • By staff
    • May 6, 2025
    • 1 views

    Google accidentally reveals details about its new Android design language, Material 3 Expressive

    • By staff
    • May 5, 2025
    • 2 views

    People struggle to get useful health advice from chatbots, study finds

    • By staff
    • May 5, 2025
    • 1 views

    11x CEO Hasan Sukkar steps down

    • By staff
    • May 5, 2025
    • 2 views

    Over 250 CEOs sign open letter supporting K-12 AI and computer science education

    • By staff
    • May 5, 2025
    • 2 views

    OpenAI reverses course, says its nonprofit will remain in control of its business operations

    • By staff
    • May 5, 2025
    • 1 views