Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage & billing
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Usage & billing
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksNano RPCEarn crypto
  1. Models
  2. Text
  3. Unsloth

Gemma 3 27B IT

Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions.

  • Native PDF input
Model weights

Pricing

Auto routing · per 1M tokens
Input
$0.299
Output
$0.299
Cache read
$0.15
Compare provider prices

Specifications

Context window
128K
Max output
96K
Parameters
27B

Benchmarks

Sourced from LMArena.

Arena Score

1365.4

Overall Rank

#205 / 421

Votes

46,613

Confidence Interval

1361.7 - 1369.1

Category Scores

Coding

#266 / 416

8,007 votes

1357.8

Math

#231 / 404

3,578 votes

1322.8

Longer Query

#212 / 399

6,664 votes

1365.5

Creative Writing

#186 / 419

6,301 votes

1348.2

Instruction Following

#217 / 421

12,488 votes

1343.4

Hard Prompts

#224 / 421

17,677 votes

1366.6

Additional Categories
22

German

#168 / 320

1,206 votes

1371.2

Polish

#170 / 244

2,827 votes

1368.8

Japanese

#173 / 288

1,052 votes

1308.2

Korean

#173 / 289

887 votes

1324.1

Industry Medicine And Healthcare

#182 / 390

2,341 votes

1406.9

French

#185 / 301

655 votes

1386.2

Industry Business And Management And Financial Operations

#193 / 414

6,490 votes

1377.8

Industry Legal And Government

#195 / 393

2,660 votes

1384.2

Industry Writing And Literature And Language

#195 / 420

10,582 votes

1354.5

Russian

#195 / 385

3,434 votes

1367.2

Industry Life And Physical And Social Science

#196 / 419

7,858 votes

1391.7

Spanish

#201 / 303

891 votes

1357.2

Exclude Ties

#205 / 421

32,630 votes

1331.2

Industry Entertainment And Sports And Media

#206 / 419

7,992 votes

1326.9

Non English

#206 / 421

23,590 votes

1349.6

Multi Turn

#207 / 419

6,721 votes

1358.1

English

#213 / 421

23,013 votes

1376.7

Chinese

#221 / 395

2,850 votes

1371.0

Hard Prompts English

#229 / 419

8,913 votes

1375.2

Industry Mathematical

#230 / 401

3,194 votes

1339.4

Industry Software And It Services

#235 / 421

14,060 votes

1376.5

Expert

#236 / 371

2,255 votes

1338.4

Published 2026-11-09 · Matched as Gemma 3 27B IT · CC BY 4.0

LMArena Dataset

Leaderboard results

BenchmarkScoreRank on NanoGPT
Epoch AI Benchmarking Hub

Epoch AI data, CC BY 4.0 · Updated Nov 12, 2026

GPQA Diamond

47.7%

#112 of 119

OTIS Mock AIME 2024–2025

22.5%

#110 of 121

EQ-Bench

EQ-Bench data, MIT · Updated Nov 12, 2026

Creative Writing v3

1266

#76 of 96

Longform Writing

41.9

#78 of 97

EQ-Bench 3

1105

#34 of 49

UGI Leaderboard

UGI Leaderboard data, Apache-2.0 · Updated Oct 16, 2026

UGI Score

20.4

#129 of 149

UGI Willingness

2.0

#119 of 149

UGI Writing

45.0

#68 of 149

Filtered and ranked to models on NanoGPT.

Providers

Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)

Auto
Auto
Recommended
$0.299$0.299$0.15N/AN/A
Auto
Auto (ZDR)
$0.299$0.299$0.15N/AN/A
Kitani
Kitani
INT4
GLB
$0.293$0.293$0.147N/AN/A
Privacy:ZDR, prompts not retainedRetains prompts, training unclear
Batch API
ProviderInputOutputCached input
Auto
Autounsloth/gemma-3-27b-it
$0.299/M$0.299/M$0.15/M

Batch rows for this model use normal routing and cost the same as standard API requests. Set provider in a row to choose a provider.

Related text models

Compare Gemma 3 27B IT with similar models from the same provider or model family.

Gemma 3 12B IT

unsloth/gemma-3-12b-it

Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions.

Gemma 3 4B IT

unsloth/gemma-3-4b-it

Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions.

Gemini 4 Carbon

google/gemini-4-carbon

Google's Gemini 4 Carbon is a reasoning model for complex coding, scientific and mathematical problem solving, and multi-step tasks that use tools. It accepts text, images, audio, video, and PDFs and produces text, with tool calling and structured outputs. Its 1,048,576-token context is shared across input, thinking, and output. Responses support up to 32,768 combined thinking and output tokens, with low, medium, and high thinking levels; medium is the default.

Gemini 4 Argon

google/gemini-4-argon

Google's Gemini 4 Argon is a flagship reasoning model for complex software engineering, mathematical and scientific problem solving, and multi-step agents. It accepts text, images, audio, video, and PDFs, with tool calling and structured outputs. Its 1,048,576-token context is shared across input, thinking, and output; synchronous output is capped at 65,536 tokens.

Gemini 3.8 Flash

google/gemini-3.8-flash

Google's fast multimodal model for agentic workloads, including coding, tool use, image understanding, PDF and document extraction, audio, and video. Its capabilities, limits, reasoning behavior, and pricing currently mirror Gemini 3.7 Flash.

Gemini 3.7 Flash

google/gemini-3.7-flash

Google's frontier-performance Flash model for multimodal and agentic workloads, including coding, tool use, image understanding, PDF and document extraction, audio, and video. Google reports 65.3% on DeepSWE v1.1, up from 49.0% for Gemini 3.6 Flash, and 34% on GDP.pdf, up from 14%.