Gemini 3.1 Pro Preview
Made by Google DeepMind. Epoch AI does not state how it can be accessed. Appears strongest at writing among the models listed here.
In short
What it does well
- Writing: Top tier (11th of 77 listed models)
Where it falls short
- Coding: Middle (41st of 77 listed models)
What we don't know yet
- Hard maths problems: Not enough data
- School-competition maths: Not enough data
- Graduate-level science questions: Not enough data
- Short factual questions: Not enough data
- Fixing real software bugs: Not enough data
- Difficult coding tasks: Not enough data
The four ratings
- Top tier
- Strong
- Middle
- Behind the leaders
- Not enough data
Ratings compare only the 77 models listed here, in quarters, best first. “Not enough data” means no result yet. It is never a low score.
- Writing
- Top tierHow often people preferred its answers to writing prompts. 1,482 on Arena's scale · Source for Gemini 3.1 Pro Preview writing score (lmarena)
- Coding
- MiddleHow often people preferred its answers to coding questions. 1,484 on Arena's scale · Source for Gemini 3.1 Pro Preview coding score (lmarena)
- Maths
- Not enough dataNo result yet for hard maths problems.
- Knowledge
- Not enough dataNo result yet for short factual questions.
Evidence completeness: Partial evidence, 7 of 13 tests have a result.
Where it is relatively stronger or weaker
This compares each kind of request with the model's own overall position among the 77 listed models, using Arena's votes. It is about performance on different languages, kinds of request and topics, not about political or social bias.
Relatively stronger
No category stands out as clearly stronger than its overall position.
Relatively weaker
- Expert-level prompts: 39th of 77 on prompts that need expert knowledge, against 16th of 77 overall. Source for Expert-level prompts
- Software and IT: 34th of 77 on software and IT questions, against 16th of 77 overall. Source for Software and IT
Show every category we can see
| Category | Position | Arena score | Votes | Source |
|---|---|---|---|---|
| Expert-level prompts Kind of request | 39th of 77 | 1,484 95% range 1,478 to 1,490 | 13,782 | Source for Expert-level prompts |
| Hard prompts Kind of request | 25th of 77 | 1,485 95% range 1,481 to 1,488 | 86,065 | Source for Hard prompts |
| Long prompts Kind of request | 21st of 77 | 1,482 95% range 1,478 to 1,486 | 58,532 | Source for Long prompts |
| Longer conversations Kind of request | 14th of 77 | 1,486 95% range 1,481 to 1,491 | 22,386 | Source for Longer conversations |
| Chinese Language | 18th of 76 | 1,528 95% range 1,521 to 1,535 | 9,208 | Source for Chinese |
| English prompts Language | 21st of 77 | 1,478 95% range 1,474 to 1,482 | 57,933 | Source for English prompts |
| French Language | 24th of 72 | 1,488 95% range 1,477 to 1,499 | 4,387 | Source for French |
| German Language | 12th of 55 | 1,491 95% range 1,477 to 1,505 | 2,198 | Source for German |
| Japanese Language | 9th of 54 | 1,493 95% range 1,476 to 1,510 | 1,656 | Source for Japanese |
| Korean Language | 11th of 54 | 1,455 95% range 1,441 to 1,470 | 2,340 | Source for Korean |
| Non-English prompts Language | 12th of 77 | 1,476 95% range 1,473 to 1,480 | 74,599 | Source for Non-English prompts |
| Russian Language | 9th of 77 | 1,497 95% range 1,491 to 1,502 | 15,237 | Source for Russian |
| Spanish Language | 14th of 70 | 1,479 95% range 1,469 to 1,490 | 4,256 | Source for Spanish |
| Entertainment, sport and media Topic | 11th of 77 | 1,466 95% range 1,461 to 1,470 | 30,803 | Source for Entertainment, sport and media |
| Law and government Topic | 19th of 76 | 1,486 95% range 1,480 to 1,493 | 10,871 | Source for Law and government |
| Medicine and health Topic | 18th of 75 | 1,486 95% range 1,479 to 1,493 | 9,860 | Source for Medicine and health |
| Science Topic | 18th of 77 | 1,497 95% range 1,492 to 1,502 | 22,070 | Source for Science |
| Software and IT Topic | 34th of 77 | 1,487 95% range 1,483 to 1,491 | 51,951 | Source for Software and IT |
Bias: what we can and can't see
Our sources do not measure political lean, stereotyping, flattery (agreeing with you too readily) or safety behaviour, so we cannot say how any model does on those. What we can show is above: where a model is relatively stronger or weaker across languages, kinds of request and topics. Also, people voting in Arena can favour answer style, such as length and formatting, and our numbers do not adjust for that. See what AI bias means and what these tests can tell you.
Best-supported use cases
- Homework and maths: not ranked, because there is not enough data for the main test.
- Research and checking facts: not ranked, because there is not enough data for the main test.
Where an alternative might be more suitable
- Coding and building things: rated Middle on coding votes. Compare it with Claude Opus 5.5, the best-supported choice for this task.
- Homework and maths: no result on hard maths problems, so we cannot say. See which models the evidence does support.
- Business emails and everyday work: rated Strong on business-task votes. Compare it with Gemini 4 Argon, the best-supported choice for this task.
- Research and checking facts: no result on short factual questions, so we cannot say. See which models the evidence does support.
What it is
- Maker
- Google DeepMind
- Access, as listed by Epoch AI
- Not stated
- Licence, as listed by Arena
- Proprietary
- Last observation in our data
- 28 Oct 2026
- Data last changed
- 29 Oct 2026, 14:36 UTC
Epoch has rows with a similar name, but Epoch's own family name differs from Arena's, so Epoch results are not used for this model.
We have not verified an official product page for this model, so we do not link to one.
How you can use it
Proprietary. The model's files are not published, so it is generally available only through its maker or partners the maker chooses.
How you can reach it (an app, a website, a developer API or a third-party tool) and what that costs are not covered by our benchmark data. Where we could verify prices from the maker's own pages, they are shown under Price. See models, apps and harnesses and how AI pricing works.
Price
Price not independently verified
See Gemini plans and pricing (checked 28 Oct 2026). Page opened and read.
We never infer subscription prices from API prices. New to “tokens” and “per million”? See how AI pricing works.
Good to remember
- Benchmarks are samples of tasks. None proves performance in every situation.
- Arena scores come from people choosing between answers. That measures preference, not correctness.
- Ratings are relative to the 77 models listed here. A different set would change them.
- Sources test models at different settings. Each result shows the setting used, and we do not adjust it.
The evidence, for the curious
Show all 13 tests with settings and sources
| Test | Result | Rating | Setting used | Source identifier | Observed | Links |
|---|---|---|---|---|---|---|
| Arena text: overall preference Arena 'text' leaderboard (Bradley-Terry rating, no style control) |
1,480 Arena score 95% range 1,477 to 1,483, 132,547 votes |
Top tier | effort: not stated, bradley-terry rating | Gemini 3.1 Pro Preview lmarena · text/latest |
28 Oct 2026 | Source for Gemini 3.1 Pro Preview Arena text: overall preference score (lmarena) |
| Arena text: creative writing Arena 'text' leaderboard, category creative_writing |
1,482 Arena score 95% range 1,477 to 1,488, 24,631 votes |
Top tier | effort: not stated, bradley-terry rating | Gemini 3.1 Pro Preview lmarena · text/latest |
28 Oct 2026 | Source for Gemini 3.1 Pro Preview Arena text: creative writing score (lmarena) |
| Arena text: coding Arena 'text' leaderboard, category coding |
1,484 Arena score 95% range 1,479 to 1,488, 36,254 votes |
Middle | effort: not stated, bradley-terry rating | Gemini 3.1 Pro Preview lmarena · text/latest |
28 Oct 2026 | Source for Gemini 3.1 Pro Preview Arena text: coding score (lmarena) |
| Arena text: maths Arena 'text' leaderboard, category math |
1,485 Arena score 95% range 1,477 to 1,493, 6,932 votes |
Strong | effort: not stated, bradley-terry rating | Gemini 3.1 Pro Preview lmarena · text/latest |
28 Oct 2026 | Source for Gemini 3.1 Pro Preview Arena text: maths score (lmarena) |
| Arena text: following instructions Arena 'text' leaderboard, category instruction_following |
1,466 Arena score 95% range 1,462 to 1,470, 45,417 votes |
Strong | effort: not stated, bradley-terry rating | Gemini 3.1 Pro Preview lmarena · text/latest |
28 Oct 2026 | Source for Gemini 3.1 Pro Preview Arena text: following instructions score (lmarena) |
| Arena text: business and management Arena 'text' leaderboard, category industry_business_and_management_and_financial_operations |
1,459 Arena score 95% range 1,454 to 1,464, 25,607 votes |
Strong | effort: not stated, bradley-terry rating | Gemini 3.1 Pro Preview lmarena · text/latest |
28 Oct 2026 | Source for Gemini 3.1 Pro Preview Arena text: business and management score (lmarena) |
| Arena WebDev: building web apps Arena 'webdev' leaderboard (Code Arena), category overall |
1,447 Arena score 95% range 1,442 to 1,452, 24,129 votes |
Middle | effort: not stated, bradley-terry rating | Gemini 3.1 Pro Preview lmarena · webdev/latest |
28 Oct 2026 | Source for Gemini 3.1 Pro Preview Arena WebDev: building web apps score (lmarena) |
| FrontierMath Tiers 1-3 (v2) | Not enough data | |||||
| OTIS Mock AIME 2024-2025 | Not enough data | |||||
| GPQA Diamond | Not enough data | |||||
| SimpleQA Verified | Not enough data | |||||
| SWE-bench Verified (Epoch runs) | Not enough data | |||||
| FrontierCode (reported by Cognition) | Not enough data | |||||
Missing evidence
Not enough data for these tests:
- FrontierMath Tiers 1-3 (v2)
- OTIS Mock AIME 2024-2025
- GPQA Diamond
- SimpleQA Verified
- SWE-bench Verified (Epoch runs)
- FrontierCode (reported by Cognition)
Missing results are not low scores and do not count against the model.
Where a source gives no public run log, we cannot show the run behind the score. See data sources.
Not sure this is the right one?
Tell us what you need help with and we'll narrow the options down.