Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d271Policy30d66, 14 pendingSources1,015

Gemini 3.1 Pro

GoogleReleased Feb 19, 2026Current

Score basis

Gemini 3.1 Pro is at the frontier in instruction following; strong in factuality, multimodal tasks, and reasoning; capable in long context and coding; and behind the leaders in agentic tasks and math. Too few results yet to rate safety or multilingual tasks.

Capability profile

Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.

Frontier1 capability
  1. Instruction FollowingLeads3 of 3
Strong3 capabilities
  1. Factuality−2.8%4 of 4
  2. Multimodal−8.6%4 of 6
  3. Reasoning−9.2%6 of 6
Capable2 capabilities
  1. Long Context−13.5%2 of 3
  2. Coding−20.4%10 of 10
Limited2 capabilities
  1. Agentic−28.4%7 of 7
  2. Math−40.0%5 of 5
Not rated2 capabilities

Too few results yet to rate Safety or Multilingual.

Price

$2.00input$12.00outputper million tokens

From Artificial Analysis · 4 providers tracked · All prices

Costs more than 85% of 330 priced models · 3:1 input-to-output blend, log scale

Evidence

217results on174benchmarks

  • 30 independently verified
  • 21 aggregator
  • 37 vendor-reported
  • 129 cross-referenced

From 37 sources · latest Oct 8, 2026 · How verification works

API features

Tool callingStructured outputsReasoning

As listed by OpenRouter

Research

84 papers reference Gemini 3.1 Pro

Gemini 3.1 Pro benchmark results

217 results on 174 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.

Instruction Following

FrontierFull instruction following ranking

Leads the field3 of 3 ranked benchmarks measured

Show 1 more instruction following resultHide 1 instruction following result

Factuality

StrongFull factuality ranking

2.8% behind the leader4 of 4 ranked benchmarks measured

Show 1 more factuality resultHide 1 factuality result

Multimodal

StrongFull multimodal ranking

8.6% behind the leader4 of 6 ranked benchmarks measured

Show 7 more multimodal resultsHide 7 multimodal results

Reasoning

StrongFull reasoning ranking

9.2% behind the leader6 of 6 ranked benchmarks measured

Show 7 more reasoning resultsHide 7 reasoning results

Long Context

CapableFull long context ranking

13.5% behind the leader2 of 3 ranked benchmarks measured

Show 1 more long context resultHide 1 long context result

Coding

CapableFull coding ranking

20.4% behind the leader10 of 10 ranked benchmarks measured

Show 7 more coding resultsHide 7 coding results

Agentic

LimitedFull agentic ranking

28.4% behind the leader7 of 7 ranked benchmarks measured

Show 9 more agentic resultsHide 9 agentic results

Math

LimitedFull math ranking

40.0% behind the leader5 of 5 ranked benchmarks measured

Show 7 more math resultsHide 7 math results

More results

Benchmarks outside the capability baskets. They are not ranked against a leader.

Show 133 more resultsHide 133 results

Gemini 3.1 Pro: common questions

Who makes Gemini 3.1 Pro?

Gemini 3.1 Pro is made by Google.

When was Gemini 3.1 Pro released?

Gemini 3.1 Pro was released on Feb 19, 2026, according to Artificial Analysis.

What is Gemini 3.1 Pro good at?

Gemini 3.1 Pro is at the frontier in instruction following; strong in factuality, multimodal tasks, and reasoning; capable in long context and coding; and behind the leaders in agentic tasks and math. Too few results yet to rate safety or multilingual tasks.

How much does Gemini 3.1 Pro cost?

Gemini 3.1 Pro costs $2.00 per million input tokens and $12.00 per million output tokens, according to Artificial Analysis. We track its price at 4 providers. At a mix of three input tokens to one output token, it costs more than 85% of the 330 priced models we track.

How many benchmarks has Gemini 3.1 Pro been tested on?

We track 217 results for Gemini 3.1 Pro on 174 benchmarks from 37 sources, 30 of them independently verified. The latest was recorded on Oct 8, 2026.

Which API features does Gemini 3.1 Pro support?

OpenRouter lists tool calling, structured outputs, and reasoning for Gemini 3.1 Pro.

About this record

Where Gemini 3.1 Pro's numbers come from, and every name it appears under.

Tracked since
Apr 26, 2026
Newest source mention
Sep 28, 2026

Where the results come from

Verification: 217 scores · 30 independently verified · 21 aggregator-attributed · 129 vendor cross-reference · 37 vendor-reported. How these tiers are assigned

From 37 sources on 19 sites. Hugging Face supplies 76 of them; the 30 independently verified results come from 10 sites. Bars are coloured by trust tier.

  • huggingface.co76
  • lf3-static.bytednsdoc.com37
  • artificialanalysis.ai22
  • api.llm-stats.com17
  • deepmind.google16
  • www-cdn.anthropic.com9
  • livebench.ai7
  • ai.meta.com4
  • labs.scale.com4
  • matharena.ai4
  • raw.githubusercontent.com4
  • storage.googleapis.com4
  • epoch.ai3
  • arcprize.org2
  • datasets-server.huggingface.co2
  • lmarena.ai2
  • thinkingmachines.ai2
  • cdn.sanity.io1
  • simple-bench.com1

Also known as

gemini 3.1 pro (thinking high)Gemini 3.1 Pro PreviewGemini 3.1 Pro Thinking (High)gemini-3.1-pro (thinking)*gemini 3.1 pro (preview)gemini-3-1-pro-previewgemini-3.1-pro highgemini~3.1~progemini 3.1 pro (high)gemini-3.1-pro-preview (high)