Gemini 3.5 Flash is now available in ThinkReview

Gemini 3.5 Flash is now available in ThinkReview

We're excited to announce that Gemini 3.5 Flash is now available in ThinkReview. Google introduced the Gemini 3.5 family on May 19, 2026 — models built to combine frontier intelligence with action for complex, agentic workflows. You can use 3.5 Flash today for AI-powered code reviews on GitHub, GitLab, Azure DevOps, and Bitbucket.

What is Gemini 3.5 Flash?

Gemini 3.5 Flash is the first model in Google's new 3.5 series. According to Google's announcement, it delivers frontier performance for agents and coding at the speed you expect from the Flash line — without trading quality for latency.

Highlights from Google's launch:

• Strongest agentic and coding model yet — Google positions 3.5 Flash as outperforming Gemini 3.1 Pro on demanding benchmarks, including Terminal-Bench 2.1 (76.2%), GDPval-AA (1656 Elo), and MCP Atlas (83.6%).
• Leading multimodal understanding — 84.2% on CharXiv Reasoning for reasoning over charts, diagrams, and visual context in codebases.
• Exceptional speed — Roughly 4× faster output tokens per second than other frontier models in Google's comparisons.
• Built for long-horizon work — Ideal for multi-step tasks that plan, build, and iterate — from maintaining large codebases to reviewing complex, multi-file changes.
• Cost-efficient at scale — Often at less than half the cost of other frontier models for comparable workloads.

Google is also working on Gemini 3.5 Pro, with a broader rollout planned for next month. 3.5 Flash is generally available now via the Gemini API, Google AI Studio, and related developer platforms.

Why use Gemini 3.5 Flash in ThinkReview

Pull request review is exactly the kind of workload 3.5 Flash targets: fast feedback on diffs, reasoning across files, security and best-practice checks, and conversational follow-up on your merge requests.

• Faster reviews — Lower latency helps large PRs feel responsive without waiting on slower flagship models.
• Deeper coding intelligence — Benchmark-leading agentic and coding scores translate to sharper suggestions on architecture, bugs, and implementation details.
• Multimodal context — Strong visual and document understanding when your changes touch diagrams, configs, or mixed assets in the diff.
• Same workflow everywhere — Pick Gemini 3.5 Flash once in ThinkReview and run it across all supported platforms.

Whether you want maximum depth on a critical change or high-throughput reviews across many PRs, Gemini 3.5 Flash is a strong default in the ThinkReview model catalog.

How to use it in ThinkReview

1. Open ThinkReview settings — Click the extension icon and go to Settings or Model selection.
2. Choose Gemini 3.5 Flash — Select it from the model dropdown for your reviews.
3. Run a review — Open any pull request or merge request and start ThinkReview with your chosen model.

You can switch between models at any time. Use 3.5 Flash when you want frontier coding quality at Flash speed; switch to Pro or other models when you need a different trade-off for a specific review.

Manage models in Model Selection on the ThinkReview portal.

Where it works

Same as always: GitHub, GitLab, Azure DevOps, and Bitbucket Cloud. One extension, one workflow — now with Google's latest agentic coding model.

If you try Gemini 3.5 Flash on real PRs and have feedback, we'd love to hear it — open an issue on GitHub or reach out via thinkreview.dev.

Ready to try frontier-speed AI code reviews? Install ThinkReview or manage your models in the portal.

Cover image from Google's Gemini 3.5 announcement.