xiji2646-netizen

xiji2646-netizen

Gemini 3.5 Flash launched today - quick breakdown for anyone running agent workloads

Google shipped 3.5 Flash at I/O 2026. The “budget” Flash model now beats 3.1 Pro on coding and tool-calling benchmarks.

Key numbers (from Google):

  • MCP Atlas (tool calling): 83.6% vs 3.1 Pro’s 78.2%
  • Terminal-Bench (coding): 76.2% vs 70.3%
  • Finance Agent v2: 57.9% vs 43.0%
  • 4x faster, ~40% cheaper than Pro
  • $1.50/M input, $9/M output, $0.15/M cached

Where it does NOT win:

  • Computer Use: not supported (GPT-5.5 only)
  • SWE-Bench Pro: Opus 4.7 still leads
  • Abstract reasoning: 3.1 Pro still edges it

My quick take on model routing:

  • Multi-tool agent loops → Flash
  • Heavy code refactoring → Opus 4.7
  • GUI automation → GPT-5.5

Anyone tested it on real agent workflows yet? Curious how the 4x speed claim holds up in practice.

Where Next?

Popular Ai topics Top

AstonJ
Loads of news stories about DeepSeek here in the last few days, no surprise as it’s been making headlines across the world! Currently a h...
New
AstonJ
This is a very quick guide, you just need to: Download LM Studio: https://lmstudio.ai/ Click on search Type DeepSeek, then select the o...
New
apoorv-2204
I’m reaching out to all software engineers, especially senior developers — I really want to hear your thoughts. I’ve always loved buildi...
New
kammy
Hi everyone! The other day I was having a debate with my friends about whether or not the top LLM models are “good at design.” I’d love ...
New
Eiji
Yesterday a very interesting to discuss situation have happen. While StackOverflow still suffer a lot, because of chat bots, but yesterda...
New
xiji2646-netizen
Woke up to this today: Claude Code’s complete source code exposed via npm source map. Not a snippet. All 512,000 lines. 1,900 TypeScript ...
New
xiji2646-netizen
Been using a two-stage workflow for AI video production that’s been consistently more reliable than text-to-video: Generate a 3×3 stor...
New
xiji2646-netizen
DeepSeek officially launched deepseek-v4-flash and deepseek-v4-pro in preview on April 24, 2026. The legacy routes (deepseek-chat, deepse...
New
xiji2646-netizen
Curious how others deal with this: you start a refactoring task with your AI coding assistant, close the terminal, come back – and it has...
New
xiji2646-netizen
Been using the skills repo (77K stars, #1 on GitHub Trending recently) with Claude Code. Sharing what worked and what did not. What work...
New

Other popular topics Top

PragmaticBookshelf
Instantly view the changes you make to an app with stateful hot reload, and define a declarative UI in the same language as the app logic...
New
siddhant3030
I’m thinking of buying a monitor that I can rotate to use as a vertical monitor? Also, I want to know if someone is using it for program...
New
dasdom
No chair. I have a standing desk. This post was split into a dedicated thread from our thread about chairs :slight_smile:
New
AstonJ
There’s a whole world of custom keycaps out there that I didn’t know existed! Check out all of our Keycaps threads here: https://forum....
New
Maartz
Hi folks, I don’t know if I saw this here but, here’s a new programming language, called Roc Reminds me a bit of Elm and thus Haskell. ...
New
AstonJ
If you get Can't find emacs in your PATH when trying to install Doom Emacs on your Mac you… just… need to install Emacs first! :lol: bre...
New
PragmaticBookshelf
Author Spotlight Jamis Buck @jamis This month, we have the pleasure of spotlighting author Jamis Buck, who has written Mazes for Prog...
New
First poster: bot
zig/http.zig at 7cf2cbb33ef34c1d211135f56d30fe23b6cacd42 · ziglang/zig. General-purpose programming language and toolchain for maintaini...
New
PragmaticBookshelf
Use advanced functional programming principles, practical Domain-Driven Design techniques, and production-ready Elixir code to build scal...
New
PragmaticBookshelf
Lint your docs like code: turn any style guide into enforceable rules with Vale and publish clear, consistent content every time. ...
New