Gemini 3.7 Flash · Automate What Academy

Aug 14 • 🤖 AI

Gemini 3.7 Flash

Google just dropped another Flash model, and it's only been three weeks since the last one.

Gemini 3.7 Flash is out, and the headline is that it beats 3.6 Flash across coding, document work, and agent tasks while launching at half the price per million tokens.

Intro pricing sits at $0.75 per 1M input tokens and $3.75 per 1M output
That intro rate ends Dec 31, 2026, then it jumps to $1.50 and $7.50
AutomationBench score went from 17.0% to 30.4%, so real business workflows nearly doubled
Coding jumped too: DeepSWE v1.1 hit 65.3% vs 49.0% on the old model
FrontierCode 1.1 came in at 43.6% vs 34.4%
WebDev Arena Elo moved from 1538 to 1588 for front end builds
PDF comprehension climbed from 22.0% to 34.0% on the GDP.pdf benchmark
Google says it plans better, calls tools more carefully, and needs fewer retries
Gemini Spark, the 24/7 personal agent, switched to 3.7 Flash today in 160+ countries
Live in AI Studio, Antigravity, and Gemini Enterprise right now

The release cadence is what gets me here. Three weeks between models means the cheap tier is now moving faster than most of us can rebuild our workflows around it.

Are you guys rebuilding for every new model drop, or waiting for things to settle down? haha

https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-3-7-flash/

2 comments

Gemini 3.7 Flash