NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/Gemma 3 4B
Google DeepMind logo

Gemma 3 4B

by Google DeepMind · Released Mar 2025

Open SourceMultimodal
4.5
avg score
Rank #309
Compare
Better than 1% of all models
Context
131K tokens (~66 books)
Input $/1M
$0.05
Output $/1M
$0.10
Type
multimodal
License
Open Source
Benchmarks
6 tested
Data as of
About

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

Tested on 6 benchmarks · BenchGecko score 4.5. Top scores: Chatbot Arena Elo — Overall (1303.2%), Dtbench (18.2%), OTIS Mock AIME 2024-2025 (7.4%).

Capabilities
math
7.4
#259 globally
knowledge
0.0
#310 globally
general
10.7
#189 globally
Benchmark Scores
Compare All
Tested on 6 benchmarks · Ranked across 4 categories
Score Distribution (all 312 models)
0255075100
▲ You are here
mathCompare math →
OTIS Mock AIME 2024-2025

Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.

7.4·
knowledgeCompare knowledge →
Chess Puzzles

Tactical chess puzzles testing pattern recognition and multi-move calculation. Measures strategic reasoning ability.

0.0·
GPQA diamond

Graduate-level science questions written by PhD experts. Diamond subset contains questions where experts disagree, testing deep understanding.

0.0·
arenaCompare arena →
Chatbot Arena Elo — Overall

Chatbot Arena overall Elo rating. Crowdsourced human preference ranking from blind head-to-head comparisons across all topics.

1303·
Quick compare:eleutherai logovs Gpt Neo 125mvs TinyLlama 1.1B Chat V1.0vs SmolLM2 135M Instruct
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Similar Models
eleutherai logo
Gpt Neo 125m
eleutherai
4.6n/a
TinyLlama 1.1B Chat V1.0
TinyLlama
3.3n/a
SmolLM2 135M Instruct
Hugging Face TB
7.6n/a
Links
Info
Google DeepMindPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@Google DeepMind
Source Code
GitHubHugging Face
BenchGecko API
gemma-3-4b-it
Specifications
  • Typemultimodal
  • Context131K tokens (~66 books)
  • ReleasedMar 2025
  • LicenseOpen Source
  • StatusActive
  • Cost / Message~$0.000
Available On
Google DeepMind logoGoogle DeepMind$0.05
Categories
mathknowledgegeneral
Learn More
context-windowtransformeropen weightstokens
Share & Export
Tweet
Related Models
eleutherai logoGpt Neo 125m
4.6
TinyLlama 1.1B Chat V1.0
3.3
SmolLM2 135M Instruct
7.6
DeepSeek logoDeepSeek Coder 1.3B
1.2
Gemma 3 4B is an open-source multimodal AI model by Google DeepMind, released in March 2025. It has an average benchmark score of 4.5. Context window: 131K tokens.

Related Models

Gpt Neo 125m · eleutheraiTinyLlama 1.1B Chat V1.0 · TinyLlamaSmolLM2 135M Instruct · Hugging Face TBDeepSeek Coder 1.3B · DeepSeekQwen2 0.5B Instruct · Alibaba

Benchmarks

Chatbot Arena Elo — OverallDtbenchOTIS Mock AIME 2024-2025LmcaChess Puzzles

Related Pages

Google DeepMind · ProviderGoogle DeepMind · EconomyAll ModelsCompare ModelsPricingDevelopers · APIContext Window · Glossary

Key facts · as of 2026-10-05

  • Gemma 3 4B by Google DeepMind. BenchGecko score 4.5, rank 309 of 312 scored models (normalized average of public benchmark scores).
  • List price $0.0500 input · $0.10 output per 1M tokens (as of 2026-10-05).
  • Sold by 1 provider (as of 2026-10-05): DeepInfra (bf16) $0.0500 in / $0.10 out.

How to cite · data as of 2026-10-05

Gemma 3 4B · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/gemma-3-4b-it

Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP