Google

Gemma 3 27B — Benchmark Scores, Pricing & Performance Analysis

OPEN SOURCEGoogle
Chatbot Arena ELO
1339
Output Speed
58 tok/s
Input Cost
$0.08/1M
Output Cost
$0.45/1M
Context Window
131K

Gemma 3 27B by Google demonstrates strong general intelligence, competitive pricing. View detailed benchmark data including scores across coding, math, reasoning, speed, and cost metrics.

General Benchmarks

AA Intelligence Index
4.965th of 66

Artificial Analysis composite intelligence score across 10 sub-benchmarks

Artificial Analysis (via OpenRouter)
Chatbot Arena ELO
133938th of 74

Human preference ELO from blind head-to-head votes

LMSYS / HuggingFace

Coding Benchmarks

AA Coding Index
10.191st of 96

Artificial Analysis composite coding score

Artificial Analysis (via OpenRouter)

Reasoning Benchmarks

AA Agentic Index
0.169th of 70

Artificial Analysis composite score for multi-step tool-using tasks

Artificial Analysis (via OpenRouter)

Speed Benchmarks

Output Speed
58 tok/s73rd of 94

Tokens generated per second

Aggregated
Time to First Token
390 ms39th of 92

Latency before first token arrives

Aggregated

Cost Benchmarks

Cached Input Cost
$0.0439th of 136

Cost per 1M cached input tokens — the price that actually applies to a long agent conversation

OpenRouter API
Input Cost
$0.08108th of 413

Cost per 1M input tokens

OpenRouter API
Output Cost
$0.45157th of 413

Cost per 1M output tokens

OpenRouter API

Context Benchmarks

Context Length
131K212th of 451

Maximum context window size

OpenRouter API

Available from 4 providers

The same model costs different amounts depending on who serves it.

ProviderInput / 1MOutput / 1MCached inContextYour key
EmpirioLabs AI$0$0—128K—
NovitaAI$0.119$0.2—98K—
GreenPT$0.342$0.684—40K—
STACKIT$0.53$0.76—37K—

Gemma 3 27B — Benchmark Scores Overview

Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).

Gemma 3 27B — Frequently Asked Questions

How intelligent is Gemma 3 27B?

Gemma 3 27B scores 1339 on the Chatbot Arena ELO rating, making it a mid-tier AI model. This score is based on blind head-to-head human preference voting.

How much does Gemma 3 27B cost?

Gemma 3 27B costs $0.08 per 1M input tokens and $0.45 per 1M output tokens. This makes it one of the more affordable models.

How fast is Gemma 3 27B?

Gemma 3 27B generates output at 58 tokens per second, which is slower, prioritizing quality over speed compared to other models. The time to first token is 390 ms.

What is the context window of Gemma 3 27B?

Gemma 3 27B has a context window of 131K tokens. This determines how much text, conversation history, and code the model can process in a single request.

Who created Gemma 3 27B?

Gemma 3 27B was created by Google. It is classified as a open source model in our catalogue.

Is Gemma 3 27B open source?

Yes, Gemma 3 27B is an open-source model. The model weights are publicly available for download and self-hosting.