menu
Can Gemma 4 Beat Gemini 3.1 Pro at Coding?

Can Gemma 4 Beat Gemini 3.1 Pro at Coding?

●1 ●5 ●14
calendar_today • schedule8 min read
— Originally published at jason.agostoni.net

2 Comments

•

Good writeup, but I wonder how much of this is model vs setup differences (CLI, env, etc.). Have you tried swapping those to isolate it?

2 votes
•

@[BlackSpecter] it is certainly possible. For sure the system prompts and tools are different which we certainly affect the token usage. Sometime in the future I could run Gemini through Copilot CLI.

0
🔥 Join developers growing publicly
Share your knowledge, build in public, and grow your developer presence with a global community.
Join CoderLegion

More Posts

Sovereign Intelligence: The Complete 25,000 Word Blueprint (Download)

Pocket Portfolio - Apr 1

I’m a Senior Dev and I’ve Forgotten How to Think Without a Prompt

Karol Modelskiverified - Mar 19

Architecting a Local-First Hybrid RAG for Finance

Pocket Portfolio - Feb 25

I spent years trying to get AI agents to collaborate. Then Opus 4.6 and Codex 5.3 wrote the rules

snapsynapse - Apr 20

The Privacy Gap: Why sending financial ledgers to OpenAI is broken

Pocket Portfolio - Feb 23
chevron_left
Jason Agostoni
1.2k Points • 20 Badges
jason.agostoni.net
5Posts
12Comments
6Connections
Principal Architect driving AI solutions for large organizations ... and myself!

More From JAgostoni

Antigravity CLI First Impressions: Fast, Rough, and Not Ready

An AI Benchmark That Tests Real Coding Workflows

Vector Similarity, Zero Client JS: Decoupled Analytics on a Side Project Budget

Related Jobs

View all jobs →

Commenters (This Week)

2 comments
2 comments
1 comment

Contribute meaningful comments to climb the leaderboard and earn badges!