> Gemini 3.5 Flash-Lite is a closed AI model from Google, released 21 Jul 2026. Index score 142 (GPT-4 = 100), rank 83 of 229 ranked models. API price $0.30 in / $2.5 out per million tokens, 1.05M context.

[Models](https://themodelindex.org/models/) /[Google](https://themodelindex.org/labs/google/)

# Gemini 3.5 Flash-Lite

Google

Released 21 Jul 2026

Closed

Flagship

Date verified

[Compare](https://themodelindex.org/compare/gemini-3-5-flash-lite-vs-kimi-k3/) [Announcement](https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-6-flash-3-5-flash-lite-3-5-flash-cyber/)

142131–154

Index score

#83 of 229 models

3/ 8

Core tests taken

3 of 6 areas · plus 9 anchor tests

−42

Versus the frontier at release

best then: Claude Fable 5

$0.30/ $2.5

Price per million tokens

input / output, list price

1.05M

Context window

tokens it reads at once

## Where it sits · on the frontier

_Chart: Model Index score of every scored model since late 2022, with the best closed and best open model over time_

o3 reached this score 15 months earlier.

## Test results · by area · tick = best by any model

Show 9 anchor tests

Reasoning & knowledge

evidence

GPQA Diamond

83%

Humanity's Last Exam

no result

Maths

evidence

FrontierMath T1-3

26%

Coding

evidence

SWE-bench Verified

no result

Terminal-Bench

no result

Agents

evidence

APEX-Agents

no result

Novel problems

evidence

ARC-AGI-2

10%

Long tasks

no evidence yet

METR time horizon

no result

Independent results from the Epoch AI benchmarking hub, best reasoning setting. The core tests are shown here; anchor tests also inform the score and can be shown above.

## What others say · rank on each leaderboard

The Model Index

independent tests, our method

#83

of 219 · 142

LMArena · Creative writing

creative writing

#57

of 386 · 1435

LMArena · Text

overall chat quality, judged by people

#63

of 388 · 1454

LMArena · Coding

coding questions in chat

#70

of 383 · 1501

LMArena · Maths

maths questions in chat

#80

of 373 · 1442

LMArena · Vision

understanding images

#35

of 149 · 1264

Artificial Analysis Intelligence Index

overall capability across ten evaluations

#50

of 207 · 22

Epoch Capabilities Index

overall capability from many benchmarks

#79

of 239 · 145.1

LMArena · WebDev

building web apps and front ends

#62

of 123 · 1440

LiveBench · Overall

overall, with fresh questions to limit contamination

#57

of 58 · 63.9

Further left is better. Leaderboards measure different things: LMArena is people voting blind between two answers, the others are test scores. Click any row for the source.

## Best at · top three among current models

Not in the top three among current models on any category we track.

Where this model places in the top three of today's models, on category leaderboards and on our core tests.

## Where to use it · prices checked 1 Oct 2026

#### From the lab

Gemini

app · subscription

↗

Google AI Studio

API

↗

#### API providers · 2 · per million tokens, in / out

G

Google

$0.54 / $4.5

cheapest

G

Google AI Studio

$0.54 / $4.5

↗

Provider prices come from OpenRouter's live listing; going direct to a provider can differ. Subscriptions are the lab's own apps.

## Facts and sources

Released

21 Jul 2026

Announcement

[blog.google ↗](https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-6-flash-3-5-flash-lite-3-5-flash-cyber/)

Release entry

Gemini 3.6 Flash + 3.5 Flash-Lite

Scored as

Gemini 3.5 Flash-Lite

Artificial Analysis index

22

Output speed

326 tokens/s

Hugging Face

closed weights

## Google releases · around this one

Gemma 4

Open

2 APR 2026

index 138

Gemini 3.5 Flash

Closed

19 MAY 2026

index 165

Gemini 3.5 Flash-Lite

Closed

21 JUL 2026

index 142

Gemini 3.6 Flash

Closed

21 JUL 2026

index 164

Gemini 3.7 Flash

Closed

13 AUG 2026

index 172

---
Source: https://themodelindex.org/models/gemini-3-5-flash-lite/ · The Model Index · data as of 2026-10-01