Gemini Pro
Google's flagship Gemini large language model, available via the Gemini app, AI Studio and API.
Liked for everyday chat and deep, obscure knowledge,123 and for cleaning up, refactoring and planning code alongside other models.456 The most common complaints are that quality seems to drop after launch789 and that tool calling in agentic coding is unreliable.101112
Why people recommend it
Knowledge and chat · 3
Commenters use it for everyday questions and chat and say it knows a lot, including obscure facts.
“I am a huge fan of Gemini Pro for chat... gemini somehow just knows the most obscure stuff.”
“I love using the Gemini pro model for quick questions”
Show 1 more
“2.5 Pro is a great model. Very competent, knows a lot, and can process tons of text”
Refactoring and review · 3
Used for cleanup, light refactoring, boilerplate and code review, often after another model writes the code.
“My go-to approach is to use Claude Code Opus 4.6 for writing and Gemini 3.1 Pro for cleaning up.”
“I use it often for light refactoring, boilerplate generation, testcase skeleton generation, code review”
Show 1 more
“3 pro is very good - a bit behind codex but still very useful.”
Reasoning and accuracy · 3
Some call it the best model they have tried for troubleshooting logic, reverse engineering and medical questions.
“Its easily the best model I have tried. And yes I am talking about 3.1 pro.”
“found Gemini 3 Pro to be the best model for that, surprisingly much better than Opus 4.5”
Show 1 more
“Gemini 3.8 flash and gemini 3.1 pro seem to lead across the other LLMs.”
Planning · 2
Used for planning, problem solving and generating project plans.
“use pro for planning, fixing, problem solving, all the difficult stuff”
“I have a planner skill I use w/ Gemini Pro to generate new plans.”
Long context · 2
Its large context window lets it take in big codebases and large volumes of text.
“I require Gemini's long context size because my approach leans heavily on in context learning to produce correct code.”
“2.5 Pro is a great model. Very competent, knows a lot, and can process tons of text”
UI design · 2
Commenters pick it for UI polish and say its design work is above other models.
“If I need some UI polish, I switch to gemini 3.1 pro.”
“Gemini 3 Pro is actually at a mid designer level.”
Caveats and dissent
Quality degradation · 3
Several users say it got worse after launch or behaved as if it had been swapped for a weaker model.
“Gemini 3 Pro Preview went from exceptional in the first month to mediocre”
Show 1 more
“Getting worse each day, it was mainly Gemini 3 Pro, switched to 3.1 when it released”
Tool calling · 3
It fails tool calls and gets stuck in loops in agentic coding tools.
“the Gemini 2.5 Pro series was the best at text, but failed half of it's tool calls”
“relatively weak tool calling capability of the Gemini 2.5 Pro model”
Show 1 more
“Gemini is consistently the worst. It gets stuck in loops, wants to wipe projects when it can’t figure out the problem”
Cost and quotas · 3
It burns reasoning tokens and uses up usage limits quickly.
“Gemini spends significantly more on reasoning tokens to produce lower quality answers”
“I can burn through the Antigravity weekly limit in 1-2 hours if I force it to use Gemini 3.1 Pro.”
Show 1 more
“But it's not just Anthropic. I had the same issue with Gemini 3.1 Pro.”
Weaker than Opus · 1
Some find it less capable than Claude Opus for general use.
“Gemini is just... dumber overall.”
Image editing · 2
One user found it did a poor job editing uploaded photos compared with Flash.
“2.5 flash works really well but 2.5 pro or 3.0 pro do a very poor job”
“2.5 flash works really well but 2.5 pro or 3.0 pro do a very poor job”
Refusals · 1
It refused to run a security vulnerability-hunting task.
“gpt-5.6, gemini pro, and opus all rejected to follow.”
Often compared with
2 moved from Gemini Flash to Gemini Pro
2 moved from Gemini Pro to Gemini Flash
1 moved from Gemini Pro to Claude Opus
1 moved from GPT-5 to Gemini Pro
1 moved from Gemini Pro to Codex
Who recommends it in their own words
Threads where it came up
- Gemini 3.1 Pro Preview 4 mentions
- Gemini 4 Argon 2 mentions
- Grok 4.7 2 mentions
- Gemini 3.7 Flash 2 mentions
- Ask HN: What is best way to provide continuous context to models? 2 mentions
- Google Got Its Groove Back and Edged Ahead of OpenAI 2 mentions
Also written as Gemini 3 Pro, Gemini Pro, Gemini 2.5 Pro, Gemini 3.0 Pro. Data: gemini-pro.json. Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.
All comments 43
“Gemini is just... dumber overall.”
“I loved Gemini 3.1 Pro”
“Its easily the best model I have tried. And yes I am talking about 3.1 pro.”
“mine has 3.1 Pro, 3.5 Flash-Lite, and 3.8 Flash (with optional extra effort)”
“Thank you, Gemini. Much appreciated.”
“the Gemini 2.5 Pro series was the best at text, but failed half of it's tool calls”
“I am a huge fan of Gemini Pro for chat... gemini somehow just knows the most obscure stuff.”
“sometimes a GPT or Gemini 3.1 Pro”
“2.5 Pro is a great model. Very competent, knows a lot, and can process tons of text”
“Gemini 3.8 flash and gemini 3.1 pro seem to lead across the other LLMs.”
“I switch back to 3.1 pro and it works fine.”
“gemini-2.5-pro, claude-opus-4.8, gpt-5.1, llama-3.3-70b”
“I'll escalate to Gemini Pro with extended thinking”
“whenever I use Gemini I've just been using 3.1 Pro”
“I used the Pro subscription for Gemini 3 Pro”
“gpt-5.6, gemini pro, and opus all rejected to follow.”
“I use it often for light refactoring, boilerplate generation, testcase skeleton generation, code review”
“I use Gemini Pro (got it with my 5TB of Google storage)”
“I told Gemini Pro I woke up after having dreamt that polynomial”
“in a conversation with Gemini 3 Pro”
“Gemini 3 Pro is actually at a mid designer level.”
“now also have access Gemini Pro and Claude Pro”
“That's what the 3.1 Pro is better for.”
“I use Opus + Gemini Pro cumulatively for 3 or 4 hours a week.”
“I used Gemini Pro to convert health data from a .csv and import it into Apple Health. Worked first try.”
“I used Antigravity CLI with gemini-3.1-pro-preview.”
“I love using the Gemini pro model for quick questions”
“I've noticed a big jump when they switched to Gemini 3.1 Pro and it really became useful.”
“fun using strong AIs like Claude and Gemini Pro in AntiGravity”
“I use GPT-5.4, GPT-5.3-Codex, Gemini-3-Pro, Opus, Sonnet, at work every week.”
“I can burn through the Antigravity weekly limit in 1-2 hours if I force it to use Gemini 3.1 Pro.”
“If I need some UI polish, I switch to gemini 3.1 pro.”
“Gemini 3.1 Pro on High have been able to solve a very straightforward and basic UI bug”
“But it's not just Anthropic. I had the same issue with Gemini 3.1 Pro.”
“They have free allowances of Claude and Gemini 3.1 Pro there”
“Gemini Pro and Flash have had 1M context for a long time”
“My go-to approach is to use Claude Code Opus 4.6 for writing and Gemini 3.1 Pro for cleaning up.”
“use pro for planning, fixing, problem solving, all the difficult stuff”
“Getting worse each day, it was mainly Gemini 3 Pro, switched to 3.1 when it released”
“I have a planner skill I use w/ Gemini Pro to generate new plans.”
“Gemini 3 Pro Preview went from exceptional in the first month to mediocre”
“Gemini is consistently the worst. It gets stuck in loops, wants to wipe projects when it can’t figure out the problem”
“relatively weak tool calling capability of the Gemini 2.5 Pro model”