Gemma 3 1B Instruct

Gemma 3 1B Instruct

Google · Released Mar 13, 2025 Professional
Intelligence #10 / 576
82.0 Our Score
Speed #186 / 273
62.6 tokens / sec
Input
— Not priced
Output
— Not priced
Context
— Not reported

Analysis Summary

Gemma 3 1B Instruct is Google's smallest open-weight model in the Gemma 3 series, released in March 2025. At 1B parameters, its intelligence index of 5.6 and coding index of 0.2 reflect fundamental capacity constraints. MMLU Pro at 0.135 and LiveCodeBench at 0.017 confirm it is not suited to general business reasoning or technical tasks. The agentic index of 10.5 is very low.

For businesses, this model's primary value is edge deployment or on-device inference where model size is a hard constraint. It can handle basic intent classification or keyword extraction, but instruction following and long-context reasoning are minimal. It is not a viable option for client-facing content, coding, or any multi-step workflow.

Teams evaluating open-weight models for business use should look to larger Gemma 3 variants or other open-weight models in the 7B-27B range, which deliver substantially better results while remaining self-hostable.

Assessed June 6, 2026

Editorial notes

Gemma 3 1B Instruct from Google is a 1-billion parameter open model with very limited reasoning and near-zero coding capability, suited only to edge deployment or the simplest classification tasks.

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence1Technical0.5Value0Content2.2
Intelligence 1/10
Technical 0.5/10
Content 2.2/10
Value 0/10

How Gemma 3 1B Instruct compares

Gemma 3 1B Instruct ranks #373 of 378 AI models we track for overall intelligence, #313 of 315 for coding, #255 of 290 for agentic tasks. Gemma 3 1B Instruct is currently free to use via OpenRouter.

Performance Indices

Source: Artificial Analysis

1 Intelligence Index
0.2 Coding Index
10.5 Agentic Index
3.3 Math Index

Benchmark Scores

Intelligence

GPQA Diamond 23.7% Graduate-level scientific reasoning
HLE 5.2% Humanity's Last Exam
MMLU Pro 13.5% Multi-task language understanding
MATH 500 48.4% Mathematical problem-solving
AIME 2025 3.3% Competition mathematics (2025)
SciCode 0.7% Scientific computing

Technical

LiveCodeBench 1.7% Live coding evaluation
τ²-Bench 10.5% Conversational agent benchmark

Content

IFBench 19.9% Instruction following

Benchmark data from Artificial Analysis and Hugging Face

How does Gemma 3 1B Instruct stack up?

Compare side-by-side with other professional models.

Compare Models

Model Information

ProviderGoogle
Release Date March 13, 2025
Status Active

Frequently asked questions about Gemma 3 1B Instruct

How much does Gemma 3 1B Instruct cost?

Gemma 3 1B Instruct is currently available for free via OpenRouter.

Is Gemma 3 1B Instruct good for coding?

On our coding benchmark index, Gemma 3 1B Instruct ranks #313 of 315 models, placing it in the broader range of the field for code generation and debugging.

Who created Gemma 3 1B Instruct?

Gemma 3 1B Instruct is developed by Google and was released on March 13, 2025.