Gemini 3.8
Ranked 40 of 72 language models by recommenders
People recommend it for strong writing and formatting, fast replies at low cost, and results they find better than rival models. Critics say it gives mid answers on hard questions.
People recommend it for strong writing and formatting, fast replies at low cost, and results they find better than rival models. Critics say it gives mid answers on hard questions.
23 people gave an opinion
- recommend it
- 17
- criticize it
- 6
- approval share
- 74%
Recommended in 2 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: not recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 17 people recommend itNeeds 10 or more, met.
- 2.8 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 2 of 13 monthsNeeds 4 or more, not met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Strong writing, formatting and commit text
“Typography, use of lists, brevity, style, even the font choice on the web harness -- all of it is A tier or even S tier.”
Comment from 8 Oct 2026 in “GPT‑6 and Intelligent UI for everyone” “Doing this has greatly improved my comment and commit text quality”
Comment from 9 Sep 2026 in “I-have-ADHD: A skill to stop coding agents from burying the answer” Fast and cheap for its quality
“Gemini 3.8 High also looks pretty good and is quite fast”
Comment from 4 Sep 2026 in “Corporate America is getting hooked on open-source AI” “Not much worse than SOTA, cheap, and fast too.”
Comment from 3 Sep 2026 in “GPT-6 Astra” Preferred over rival models by users
“Opus and Gemini 3.8 (and now Argon) did a significantly better job.”
Comment from 28 Oct 2026 in “Is my data used for model training?” “out of all examples Gemini 3.8 is the best for me”
Comment from 14 Sep 2026 in “Show HN: Pelican-bicycle alternatives” “I swear even Gemini 3.8 is slightly better.”
Comment from 28 Sep 2026 in “Ember-1” - Comment from 15 Sep 2026 in “Gemini 3.8 Live and 3.8 Live Extended Thinking”
Solves hard coding tasks quickly
“which also murders DeepSWE and Terminal Bench 2.0”
Comment from 10 Sep 2026 in “Cognition launches new SWE-2 model, Rivaling Fable 5.1 and GPT-Astra” “LLM oneshoted it in about 45min”
Comment from 22 Sep 2026 in “OpenAI GPT–6 Astra breaks Enigma message that has resisted solution since 2005”
Other language models people recommend
The four most recommended other language models, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Claude Opus | 3,331 | 2,746 | 55% | 13 | 4 mo156 owners | — |
| OpenAI GPT | 1,205 | 987 | 55% | 13 | 6 mo47 owners | — |
| Claude Sonnet | 854 | 586 | 59% | 13 | 6 mo46 owners | — |
| DeepSeek V4 Flash | 828 | 223 | 79% | 8 | 1 mo24 owners | Approved |
| Gemini 3.8This page | 17 | 6 | 74% | 2 | — | — |
What people said
21 of the 24 comments that mention it, newest first. Each links to the original comment.
“3.8 medium is my daily driver. This gets me pretty far.”
“Opus and Gemini 3.8 (and now Argon) did a significantly better job.”
“gemini 3.8 has been falling way behind opus and sol in my experience”
“Gemini on the other hand somehow always outputs at the level that I am expecting and reasoning.”
“Typography, use of lists, brevity, style, even the font choice on the web harness -- all of it is A tier or even S tier.”
“The answer is always extremely mid, and the harder the question (or more effort needed to answer it), Google just quits.”
“which is very good at recognizing data to be redacted”
“it ranked Cosmic 12th in the first and 7th in the second. Very trustworthy stuff.”
“I swear even Gemini 3.8 is slightly better.”
“anti-gravity with gemini 3.8 or gtfo”
“LLM oneshoted it in about 45min”
“after trying it, I went back to G3.8”
“out of all examples Gemini 3.8 is the best for me”
“Gemini 3.8 is under appreciated”
“which also murders DeepSWE and Terminal Bench 2.0”
“Doing this has greatly improved my comment and commit text quality”
“It feels like the model has Alzheimer's. It gets confused about whether what it reads is what it did.”
“Gemini 3.8 High also looks pretty good and is quite fast”
“Not much worse than SOTA, cheap, and fast too.”
“sounds like it's very good and a great deal”
“it failed spectacularly and also halucinated the server i/o limits”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.