> Gemma 2 is an open-weights AI model from Google, released 27 Jun 2024. Index score 97 (GPT-4 = 100), rank 190 of 229 ranked models. API price $0.65 in / $0.65 out per million tokens, 8K context.

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

# Gemma 2

Google

Released 27 Jun 2024

Open

Date verified

[Compare](https://themodelindex.org/compare/gemma-2-vs-claude-3-5-sonnet/) [Announcement](https://blog.google/innovation-and-ai/technology/developers-tools/google-gemma-2/)

9785–109

Index score

#190 of 229 models

1/ 8

Core tests taken

1 of 6 areas · plus 5 anchor tests

−14

Versus the frontier at release

best then: Claude 3.5 Sonnet (Jun 2024)

Replaced by [Gemma 3](https://themodelindex.org/models/gemma-3/)

$0.65/ $0.65

Price per million tokens

input / output, list price

8K

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_

GPT-4 reached this score 15 months earlier.

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

Show 5 anchor tests

Reasoning & knowledge

evidence

GPQA Diamond

36%

Humanity's Last Exam

no result

Maths

evidence

FrontierMath T1-3

no result

Coding

no evidence yet

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

#190

of 219 · 97

LMArena · Creative writing

creative writing

#223

of 386 · 1293

Epoch Capabilities Index

overall capability from many benchmarks

#158

of 239 · 122.1

LMArena · Text

overall chat quality, judged by people

#264

of 388 · 1289

LMArena · Maths

maths questions in chat

#270

of 373 · 1248

LMArena · Coding

coding questions in chat

#282

of 383 · 1304

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

Replaced by Gemma 3; it no longer leads any category among current models.

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

#### API providers · 1 · per million tokens, in / out

N

NextBit

$0.65 / $0.65 · int4

cheapest

#### Run it yourself

🤗

Official weights

google/gemma-2-27b-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

27 Jun 2024

Announcement

[blog.google ↗](https://blog.google/innovation-and-ai/technology/developers-tools/google-gemma-2/)

Release entry

Gemma 2

Scored as

Gemma 2 27B

Artificial Analysis index

–

Output speed

–

Hugging Face

[google/gemma-2-27b-it ↗](https://huggingface.co/google/gemma-2-27b-it)

## Google releases · around this one

Gemma

Open

21 FEB 2024

Gemini 1.5 Flash

Closed

14 MAY 2024

index 98

Gemma 2

Open

27 JUN 2024

index 97

Gemini 2.0 Flash (Dec 2024)

Closed

11 DEC 2024

index 121

Gemini 2.0 Flash Thinking

Closed

19 DEC 2024

---
Source: https://themodelindex.org/models/gemma-2/ · The Model Index · data as of 2026-10-01