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 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.

  • Native PDF input
Model weights

Pricing

Auto routing · per 1M tokens
Input
$0.201
Output
$0.201
Cache read
$0.10
Compare provider prices

Specifications

Context window
128K
Max output
8.2K
Parameters
4B

Benchmarks

Sourced from LMArena.

Arena Score

1303.3

Overall Rank

#289 / 421

Votes

4,171

Confidence Interval

1294.0 - 1312.6

Category Scores

Coding

#332 / 416

605 votes

1273.5

Math

#296 / 404

423 votes

1254.1

Longer Query

#280 / 399

444 votes

1312.0

Creative Writing

#277 / 419

666 votes

1274.4

Instruction Following

#304 / 421

1,233 votes

1267.5

Hard Prompts

#305 / 421

1,092 votes

1284.2

Additional Categories
16

German

#234 / 320

162 votes

1290.3

Industry Medicine And Healthcare

#234 / 391

197 votes

1354.2

Industry Business And Management And Financial Operations

#241 / 414

390 votes

1330.3

Russian

#247 / 385

307 votes

1313.9

Industry Legal And Government

#248 / 393

245 votes

1340.1

Industry Writing And Literature And Language

#272 / 420

1,080 votes

1297.5

Non English

#275 / 421

1,599 votes

1291.3

Industry Life And Physical And Social Science

#289 / 419

780 votes

1316.2

Industry Mathematical

#289 / 402

365 votes

1274.7

Exclude Ties

#291 / 421

2,830 votes

1234.7

English

#299 / 421

2,572 votes

1309.6

Multi Turn

#302 / 419

565 votes

1272.2

Expert

#303 / 371

208 votes

1260.6

Industry Entertainment And Sports And Media

#306 / 419

761 votes

1247.8

Industry Software And It Services

#309 / 421

986 votes

1300.3

Hard Prompts English

#311 / 419

764 votes

1284.9

Published 2026-11-11 · Matched as Gemma 3 4B 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 13, 2026

GPQA Diamond

23.2%

#119 of 119

OTIS Mock AIME 2024–2025

7.5%

#115 of 121

EQ-Bench

EQ-Bench data, MIT · Updated Nov 13, 2026

Creative Writing v3

1066

#84 of 96

Longform Writing

34.4

#89 of 97

EQ-Bench 3

1001

#41 of 49

UGI Leaderboard

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

UGI Score

16.9

#140 of 149

UGI Willingness

3.0

#78 of 149

UGI Writing

24.0

#140 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
$0.201$0.201$0.10N/AN/A
Kitani
Kitani
INT4
GLB
$0.19$0.19$0.0948N/AN/A
Privacy:ZDR, prompts not retained
Batch API
ProviderInputOutputCached input
Auto
Autounsloth/gemma-3-4b-it
$0.201/M$0.201/M$0.10/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 4B 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 27B IT

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.

Gemini 4 Hydrogen

google/gemini-4-hydrogen

Google's Gemini 4 Hydrogen is a reasoning model for coding, 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, with up to 65,536 combined thinking and output tokens per response. Choose low, medium, high, or extra-high thinking; high is the default.

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.