Skip to content
LLM Report

Topic: Benchmarks

  1. Nov 13

    Google releases Gemini 4 Hydrogen, a fast model that replaces 3.8 Flash and upgrades Search

    Google launched Gemini 4 Hydrogen on 12 November 2026 as its fast, cheaper tier. It reaches the Gemini API, the Gemini app and Search for all users, and replaces Gemini 3.8 Flash across Google's products.

    Models4 sources

  2. Nov 11

    Google DeepMind releases Gemini Robotics 2.5 to robotics partners with new safety benchmark

    Google DeepMind says its Gemini Robotics 2.5 model lifts task success rates by 30% to 100% and reached 96% in a Mercedes-Benz factory pilot. It is limited to robotics partners for now.

    Models2 sources

  3. Nov 9

    AI in November: schools get an opt-out, Apple bets on AI, open tooling matures

    This month's analysis covers Google's AI-or-Search choice for schools, Apple's earnings and always-listening Watch features, and open benchmarks and adapters for developers. Each affects how teams adopt AI.

    AI assistants5 sources

  4. Nov 4

    Collinear AI releases CWE-bench v2, a public security-repair benchmark where Gemini 4 Argon leads

    Collinear AI opened 100 tasks from CWE-bench v2 to the public on 3 November 2026. In its own tests of 11 models, Gemini 4 Argon scored highest, with Claude Opus 5.5 close behind.

    Models