> Gemma 4 26B A4B is an open-weights AI model from Google, released 2 Apr 2026. Index score 136 (GPT-4 = 100), rank 100 of 229 ranked models. API price $0.076 in / $0.26 out per million tokens, 262K context.

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

# Gemma 4 26B A4B

Google

Released 2 Apr 2026

Open

[Compare](https://themodelindex.org/compare/gemma-4-26b-a4b-vs-gpt-5-5/) [Run it yourself →](https://themodelindex.org/local/)

136124–148

Index score

#100 of 229 models

1/ 8

Core tests taken

1 of 6 areas · plus 5 anchor tests

−35

Versus the frontier at release

best then: GPT-5.4

$0.076/ $0.26

Price per million tokens

input / output, list price

262K

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_

Gemini 2.5 Pro reached this score 12 months earlier.

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

Show 5 anchor tests

Reasoning & knowledge

evidence

GPQA Diamond

73%

Humanity's Last Exam

no result

Maths

evidence

FrontierMath T1-3

no result

Coding

evidence

SWE-bench Verified

no result

Terminal-Bench

no result

Agents

evidence

APEX-Agents

no result

Novel problems

no evidence yet

ARC-AGI-2

no result

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

#100

of 219 · 136

LMArena · Maths

maths questions in chat

#49

of 373 · 1468

LMArena · Text

overall chat quality, judged by people

#88

of 388 · 1437

LMArena · Coding

coding questions in chat

#93

of 383 · 1483

LMArena · Creative writing

creative writing

#98

of 386 · 1399

Artificial Analysis Intelligence Index

overall capability across ten evaluations

#66

of 207 · 17

LMArena · Vision

understanding images

#52

of 149 · 1242

Epoch Capabilities Index

overall capability from many benchmarks

#97

of 239 · 141.8

LMArena · WebDev

building web apps and front ends

#91

of 123 · 1359

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 · 13 · per million tokens, in / out

D

Darkbloom

$0.042 / $0.22

cheapest

D

DekaLLM

$0.060 / $0.33 · bf16

↗

D

DeepInfra

$0.070 / $0.34 · fp8

↗

M

Makora

$0.080 / $0.32

↗

N

NextBit

$0.090 / $0.30 · bf16

↗

C

CoreWeave

$0.10 / $0.30 · bf16

↗

C

Cloudflare

$0.10 / $0.30

↗

V

Venice

$0.13 / $0.40 · bf16

↗

#### Run it yourself

🤗

Official weights

google/gemma-4-26B-A4B-it

↗

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

2 Apr 2026

Announcement

not linked yet

Release entry

–

Scored as

Gemma 4 26B A4B

Artificial Analysis index

17 (their estimate)

Output speed

–

Hugging Face

[google/gemma-4-26B-A4B-it ↗](https://huggingface.co/google/gemma-4-26B-A4B-it)

## Google releases · around this one

PaLM 2

Closed

10 MAY 2023

Gemini 1.0 Nano

Closed

6 DEC 2023

---
Source: https://themodelindex.org/models/gemma-4-26b-a4b/ · The Model Index · data as of 2026-10-01