Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d261Policy30d65, 14 pendingSources1,013

Gemini 3.5 Flash Lite

GoogleReleased Jul 21, 2026Current

Score basis

Gemini 3.5 Flash Lite is capable in long context and factuality; and behind the leaders in multimodal tasks, agentic tasks, coding, instruction following, and math. Too few results yet to rate reasoning, 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.

Capable2 capabilities
  1. Long Context−17.8%1 of 3
  2. Factuality−20.8%2 of 4
Limited5 capabilities
  1. Multimodal−27.8%2 of 6
  2. Agentic−33.6%4 of 7
  3. Coding−40.7%7 of 10
  4. Instruction Following−41.6%1 of 3
  5. Math−61.0%3 of 5
Not rated3 capabilities

Too few results yet to rate Reasoning, Safety or Multilingual.

Price

$0.30input$2.50outputper million tokens

From Artificial Analysis · 3 providers tracked · All prices

Costs more than 55% of 331 priced models · 3:1 input-to-output blend, log scale

Evidence

58results on43benchmarks

  • 21 independently verified
  • 16 aggregator
  • 8 vendor-reported
  • 13 cross-referenced

From 16 sources · latest Oct 8, 2026 · How verification works

API features

Tool callingStructured outputsReasoning

As listed by OpenRouter

Research

2 papers reference Gemini 3.5 Flash Lite

Gemini 3.5 Flash Lite benchmark results

58 results on 43 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.

Long Context

CapableFull long context ranking

17.8% behind the leader1 of 3 ranked benchmarks measured

Factuality

CapableFull factuality ranking

20.8% behind the leader2 of 4 ranked benchmarks measured

Multimodal

LimitedFull multimodal ranking

27.8% behind the leader2 of 6 ranked benchmarks measured

Show 1 more multimodal resultHide 1 multimodal result

Agentic

LimitedFull agentic ranking

33.6% behind the leader4 of 7 ranked benchmarks measured

Coding

LimitedFull coding ranking

40.7% behind the leader7 of 10 ranked benchmarks measured

Show 3 more coding resultsHide 3 coding results

Instruction Following

LimitedFull instruction following ranking

41.6% behind the leader1 of 3 ranked benchmarks measured

Math

LimitedFull math ranking

61.0% behind the leader3 of 5 ranked benchmarks measured

Show 2 more math resultsHide 2 math results

Reasoning

Not enough dataFull reasoning ranking

0 of 6 ranked benchmarks measured

Show 8 more reasoning resultsHide 8 reasoning results

More results

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

Show 15 more resultsHide 15 results

Gemini 3.5 Flash Lite: common questions

Who makes Gemini 3.5 Flash Lite?

Gemini 3.5 Flash Lite is made by Google.

When was Gemini 3.5 Flash Lite released?

Gemini 3.5 Flash Lite was released on Jul 21, 2026, according to Artificial Analysis.

What is Gemini 3.5 Flash Lite good at?

Gemini 3.5 Flash Lite is capable in long context and factuality; and behind the leaders in multimodal tasks, agentic tasks, coding, instruction following, and math. Too few results yet to rate reasoning, safety, or multilingual tasks.

How much does Gemini 3.5 Flash Lite cost?

Gemini 3.5 Flash Lite costs $0.30 per million input tokens and $2.50 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 55% of the 331 priced models we track.

How many benchmarks has Gemini 3.5 Flash Lite been tested on?

We track 58 results for Gemini 3.5 Flash Lite on 43 benchmarks from 16 sources, 21 of them independently verified. The latest was recorded on Oct 8, 2026.

Which API features does Gemini 3.5 Flash Lite support?

OpenRouter lists tool calling, structured outputs, and reasoning for Gemini 3.5 Flash Lite.

About this record

Where Gemini 3.5 Flash Lite's numbers come from, and every name it appears under.

Tracked since
Jul 21, 2026
Newest source mention
Aug 7, 2026

Where the results come from

Verification: 58 scores · 21 independently verified · 16 aggregator-attributed · 13 vendor cross-reference · 8 vendor-reported. How these tiers are assigned

From 16 sources on 11 sites. Artificial Analysis supplies 17 of them; the 21 independently verified results come from 6 sites. Bars are coloured by trust tier.

  • artificialanalysis.ai17
  • thinkingmachines.ai10
  • arcprize.org8
  • livebench.ai7
  • api.llm-stats.com5
  • huggingface.co3
  • blog.google2
  • datasets-server.huggingface.co2
  • epoch.ai2
  • lmarena.ai1
  • storage.googleapis.com1

Also known as

How our sources name Gemini 3.5 Flash Lite at each reasoning setting.

SettingShort form
minimalgemini 3.5 flash-lite (minimal)
lowgemini 3.5 flash-lite (low)
mediumgemini 3.5 flash-lite (medium)
highgemini 3.5 flash-lite (high)
Also listed asgemini-3-5-flash-litegemini-3.5-flash-lite:batch