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
I saw this clip of Elon Musk talking about AI and wondered what others think - are you looking forward to AI? Or do you find it concerning?
New
AstonJ
I have a feeling we’re going to see a lot of threads about DeepSeek, so have put up a portal for it :003:
New
AstonJ
Curious what kind of results others are getting, I think actually prefer the 7B model to the 32B model, not only is it faster but the qua...
New
apoorv-2204
General thoughts on google gemini ? IMHO , when compared chatgpt and claude sonnnet its pretty shit, and its feels broken,
#ai
New
AstonJ
Tucker: You’ve had complaints from one programmer who said you steal people’s stuff without paying them and he winded up being murdered.
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
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 Claude Code on Max for a few weeks and kept running into rate limits by early afternoon. Same tasks as colleagues who weren’t ...
New
xiji2646-netizen
Anthropic shipped something called Dreaming for Managed Agents this week. It’s a scheduled background process that runs between sessions ...
New
LatentLogic
I recently integrated Seedance 2.5 into one of my own projects. The basic API flow is simple: create a task, get the task ID, and poll un...
New

Other popular topics Top

PragmaticBookshelf
Ruby, Io, Prolog, Scala, Erlang, Clojure, Haskell. With Seven Languages in Seven Weeks, by Bruce A. Tate, you’ll go beyond the syntax—and...
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
This looks like a stunning keycap set :orange_heart: A LEGENDARY KEYBOARD LIVES ON When you bought an Apple Macintosh computer in the e...
New
Exadra37
I am asking for any distro that only has the bare-bones to be able to get a shell in the server and then just install the packages as we ...
New
AstonJ
In case anyone else is wondering why Ruby 3 doesn’t show when you do asdf list-all ruby :man_facepalming: do this first: asdf plugin-upd...
New
PragmaticBookshelf
Learn different ways of writing concurrent code in Elixir and increase your application's performance, without sacrificing scalability or...
New
PragmaticBookshelf
Author Spotlight Mike Riley @mriley This month, we turn the spotlight on Mike Riley, author of Portable Python Projects. Mike’s book ...
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
PragmaticBookshelf
Lint your docs like code: turn any style guide into enforceable rules with Vale and publish clear, consistent content every time. ...
New
xiji2646-netizen
There’s a GitHub repo at forrestchang/andrej-karpathy-skills that’s sitting at 97.8k stars. It’s a single CLAUDE.md file with four behavi...
New