We Use Cookies

    We use cookies to enhance your browsing experience, analyze site traffic, and personalize content. By clicking "Accept All", you consent to our use of cookies. You can customize your preferences or reject non-essential cookies.

    Learn more about our cookie policy
    Models · Google · Open weights

    Gemma 4 on AI·Collab — now AGENTIC

    Google’s newest open family brings a giant leap in reasoning, coding, and especially autonomous tool use. Two flagship sizes are live on AI·Collab with full AGENTIC tools — memory, knowledge, chat history, and more.

    Model selection
    ≈ 7 min read
    AGENTIC
    ZDR · Paid tier

    What we shipped

    Gemma 4 31B and Gemma 4 26B A4B (instruction-tuned / “thinking” variants) are available on AI·Collab with native function calling enabled — the same AGENTIC experience you know from GPT-5, Claude 4.5+, and Gemini 3. Built on research from Gemini 3, Gemma 4 is Google DeepMind’s push for intelligence per parameter: a dense 31B flagship and a mixture-of-experts 26B model that activates only a fraction of weights per step — so you get frontier-level answers without always paying for a full dense run.

    In the picker, look for Google: Gemma 4 31B and Google: Gemma 4 26B A4B. Model IDs include google/gemma-4-31b-it and google/gemma-4-26b-a4b-it — always check the live catalog for exact labels and credits.

    Why “AGENTIC” matters here

    On τ2-bench (agentic tool use, retail scenario published by Google), Gemma 4 jumps from single-digit baselines for Gemma 3 to roughly 85–86% for the 26B and 31B instruction models — a step change in how reliably the model can follow multi-step workflows. In AI·Collab, AGENTIC mode means OpenWebUI injects our native tool suite: memories, knowledge bases, chat history, notes, and structured actions — so the model can decide when to recall, search, or organize instead of you clicking everything by hand.

    Strong upgrade for coding (LiveCodeBench v6) and math (AIME 2026) vs Gemma 3 — useful for drafts, refactors, and quantitative reasoning.
    Long context — up to 256K tokens on the larger Gemma 4 variants — for serious documents and multi-file work.
    Multimodal text + image on these tiers — describe, compare, and extract from screenshots and visuals.
    Designed with native function calling in mind — aligned with agentic assistants and automation.

    Read: AGENTIC AI — memory, knowledge & chat tools →

    Performance snapshot (instruction-tuned / thinking)

    Highlights from Google DeepMind’s published Gemma 4 comparisons versus Gemma 3 27B — rounded for readability. Full methodology and additional benchmarks are in the official model card.

    BenchmarkGemma 4 31B ITGemma 4 26B A4B ITGemma 3 27B IT
    Arena AI (text)145214411365
    MMMLU (multilingual Q&A)85.2%82.6%67.6%
    MMMU Pro (multimodal reasoning)76.9%73.8%49.7%
    AIME 2026 (mathematics)89.2%88.3%20.8%
    LiveCodeBench v6 (coding)80.0%77.1%29.1%
    GPQA Diamond (science)84.3%82.3%42.4%
    τ2-bench — agentic tool use (retail)86.4%85.5%6.6%

    Source: Google DeepMind Gemma 4 overview and model documentation (figures as published; scenarios and dates may be updated by Google).

    Dive deeper (official & community)

    These links are independent references — useful if you want architecture detail, license terms, or local run options:

    Try it in two minutes

    Open https://chat.aicollab.app and sign in.
    Pick Google: Gemma 4 31B or Google: Gemma 4 26B A4B — look for the purple AGENTIC badge and ZDR / paid labels.
    Enable Memory in OpenWebUI settings if you want autonomous recall across chats.
    Keep the web search toggle OFF for native agentic research; use our guide if you prefer plugin search instead.

    Browse all models and live credit rates →

    Benchmarks and capabilities describe Google’s published evaluations; your results depend on prompt, settings, and task. Pricing and availability are always defined by the in-product model catalog.

    Related Articles

    Ready to Experience 300+ AI Models?

    Get started today. Access models from OpenAI, Google, Anthropic, Grok and more.

    GDPR compliant · Zero data retention · Cancel anytime