Gemma 3 1B Instruct

Gemma 3 1B Instruct

Google · Released Mar 13, 2025
Intelligence #748 / 756
6.1 our score
Speed #223 / 330
62.6 tok/s
Input Price
Not priced
Output Price
Not priced
Context
Not reported

Analysis Summary

Gemma 3 1B Instruct is a compact Google model designed for lightweight instruction-based use. The supplied results show low performance across general reasoning, mathematics, coding, instruction following, and tool-oriented evaluation, so it cannot be treated as a general business assistant.

Its likely role is limited to simple local classification, short transformations, or highly constrained automation where cost and resource use outweigh answer quality. The record provides no pricing, context, modality, or deployment details, and the measured capability does not support client-facing generation or complex workflow control.

Use it only when a small footprint is the primary requirement and outputs can be tightly validated. It should not be selected for content production, coding, or autonomous agents.

Assessed September 7, 2026

Editorial notes

Gemma 3 1B Instruct is a very small model with low measured reasoning, coding, and instruction-following results. Its compact profile may suit simple local tasks, but it is not appropriate for demanding client content or agent workflows.

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

DFO Verdict

Gemma 3 1B Instruct is a very small model with low measured reasoning, coding, and instruction-following results. Its compact profile may suit simple local tasks, but it is not appropriate for demanding client content or agent workflows.

#748 of 756 overall Down 48 this week

Benchmark scores

GPQA Diamond 23.7%
HLE 5.2%
MMLU Pro 13.5%
MATH 500 48.4%
AIME 2025 3.3%
SciCode 0.7%
LiveCodeBench 1.7%
τ²-Bench 10.5%
IFBench 19.9%

Magenta = intelligence · Ink = technical/agentic · Cyan = content & long-context · Grey = community benchmarks. Data: Artificial Analysis, Hugging Face.

1 Intelligence Index·3.3 Math Index

How Gemma 3 1B Instruct compares

Gemma 3 1B Instruct ranks #355 of 435 AI models we track for overall intelligence. Gemma 3 1B Instruct is currently free to use via OpenRouter.

Position in the field
Intelligence: smarter than 1% of models #748
Speed: faster than 32% of models #223
worst in fieldmedianbest in field
Price vs frontier peers · $ per 1M tokens
Gemma 3 1B Instruct $0.00 in $0.00 out
OpenAI: GPT-6 Astra $10.00 in $50.00 out
Anthropic: Claude Fable 5.1 $10.00 in $50.00 out
Claude Opus 5 $5.00 in $25.00 out

Dark bar = input · light bar = output, scaled to the priciest peer.

Context window vs peers · tokens

1M tokens ≈ 8 full-length novels or ~2,500 pages of business documents in a single request.

Intelligence0.6Technical0Value0Content1.8
Performance profile

Strongest on business fit. The pulled-in value corner is the trade-off, and if the shape matters more than the price, this is your model.

Compare shapes side-by-side →

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.

Who created Gemma 3 1B Instruct?

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

© 2026 Design for Online Ltd. Registered in England and Wales No. 10328553. VAT Registered. Design for Online® and Forerunner® are registered trademarks.