Technology and Innovation Community

 View Only
Back to discussions
Expand all | Collapse all

A major update to Google's Gemini 3 Deep Think reasoning mode, posting dominant scores across math, coding, and science

  • 1.  A major update to Google's Gemini 3 Deep Think reasoning mode, posting dominant scores across math, coding, and science

    Posted 15-02-2026 22:54

    A major update released by Google this week (link below):

    Google blog

    The updated Deep Think mode continues to push the frontiers of intelligence, reaching new heights across the most rigorous academic benchmarks, including:

    • Setting a new standard (48.4%, without tools) on Humanity's Last Exam, a benchmark designed to test the limits of modern frontier models
    • Achieving an unprecedented 84.6% on ARC-AGI-2, verified by the ARC Prize Foundation
    • Attaining a staggering Elo of 3455 on Codeforces, a benchmark consisting of competitive programming challenges
    • Reaching gold-medal level performance on the International Math Olympiad 2025

    10
    - Todor



    ------------------------------
    Todor Kostov
    Director
    ------------------------------


Related Content