Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models784Deals30d245Policy30d63, 13 pendingSources1,074

Gemini 3.8 Flash

GoogleReleased Sep 2, 2026Current

Score basis

Gemini 3.8 Flash is strong in factuality, reasoning, and long context; capable in multimodal tasks and agentic tasks; and behind the leaders in instruction following, coding, 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.

Strong3 capabilities
  1. Factuality−4.0%3 of 4
  2. Reasoning−5.9%6 of 6
  3. Long Context−9.1%1 of 3
Capable2 capabilities
  1. Multimodal−17.0%2 of 6
  2. Agentic−21.1%3 of 7
Limited3 capabilities
  1. Instruction Following−26.8%1 of 3
  2. Coding−29.3%5 of 10
  3. Math−43.3%5 of 5
Not rated2 capabilities

Too few results yet to rate Safety or Multilingual.

Price

$0.75input$3.75outputper million tokens

From Artificial Analysis · 3 providers tracked · All prices

Costs more than 66% of 331 priced models · 3:1 input-to-output blend, log scale

Evidence

89results on46benchmarks

  • 28 independently verified
  • 48 aggregator
  • 13 vendor-reported

From 17 sources · latest Oct 19, 2026 · How verification works

API features

Tool callingStructured outputsReasoning

As listed by OpenRouter

Research

12 papers reference Gemini 3.8 Flash

Gemini 3.8 Flash benchmark results

89 results on 46 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.

Factuality

StrongFull factuality ranking

4.0% behind the leader3 of 4 ranked benchmarks measured

Show 4 more factuality resultsHide 4 factuality results

Reasoning

StrongFull reasoning ranking

5.9% behind the leader6 of 6 ranked benchmarks measured

Show 14 more reasoning resultsHide 14 reasoning results

Long Context

StrongFull long context ranking

9.1% behind the leader1 of 3 ranked benchmarks measured

Show 2 more long context resultsHide 2 long context results

Multimodal

CapableFull multimodal ranking

17.0% behind the leader2 of 6 ranked benchmarks measured

Show 3 more multimodal resultsHide 3 multimodal results

Agentic

CapableFull agentic ranking

21.1% behind the leader3 of 7 ranked benchmarks measured

Show 7 more agentic resultsHide 7 agentic results

Instruction Following

LimitedFull instruction following ranking

26.8% behind the leader1 of 3 ranked benchmarks measured

Coding

LimitedFull coding ranking

29.3% behind the leader5 of 10 ranked benchmarks measured

Show 5 more coding resultsHide 5 coding results

Math

LimitedFull math ranking

43.3% behind the leader5 of 5 ranked benchmarks measured

More results

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

Show 25 more resultsHide 25 results

Gemini 3.8 Flash: common questions

Who makes Gemini 3.8 Flash?

Gemini 3.8 Flash is made by Google.

When was Gemini 3.8 Flash released?

Gemini 3.8 Flash was released on Sep 2, 2026, according to Google's own announcement.

What is Gemini 3.8 Flash good at?

Gemini 3.8 Flash is strong in factuality, reasoning, and long context; capable in multimodal tasks and agentic tasks; and behind the leaders in instruction following, coding, and math. Too few results yet to rate safety or multilingual tasks.

How much does Gemini 3.8 Flash cost?

Gemini 3.8 Flash costs $0.75 per million input tokens and $3.75 per million output tokens, according to Artificial Analysis. We track its price at 3 providers. At a mix of three input tokens to one output token, it costs more than 66% of the 331 priced models we track.

How many benchmarks has Gemini 3.8 Flash been tested on?

We track 89 results for Gemini 3.8 Flash on 46 benchmarks from 17 sources, 28 of them independently verified. The latest was recorded on Oct 19, 2026.

Which API features does Gemini 3.8 Flash support?

OpenRouter lists tool calling, structured outputs, and reasoning for Gemini 3.8 Flash.

About this record

Where Gemini 3.8 Flash's numbers come from, and every name it appears under.

Tracked since
Aug 28, 2026
Newest source mention
Sep 14, 2026

Where the results come from

Verification: 89 scores · 28 independently verified · 48 aggregator-attributed · 13 vendor-reported. How these tiers are assigned

From 17 sources on 11 sites. Artificial Analysis supplies 49 of them; the 28 independently verified results come from 8 sites. Bars are coloured by trust tier.

  • artificialanalysis.ai49
  • arcprize.org12
  • api.llm-stats.com9
  • livebench.ai7
  • deepmind.google3
  • epoch.ai3
  • datasets-server.huggingface.co2
  • labs.scale.com1
  • lmarena.ai1
  • simple-bench.com1
  • storage.googleapis.com1

Also known as

How our sources name Gemini 3.8 Flash at each reasoning setting.

SettingShort formAPI id
lowgemini 3.8 flash (low)gemini-3-8-flash-low
mediumgemini 3.8 flash (medium)gemini-3-8-flash-medium
highgemini 3.8 flash (high)gemini-3.8-flash-high
Also listed asgemini-3-8-flashgemini 3.8gemini-3.8-flash:batchgemini 3.8 8 flash