Google: Gemma 3 27B
Analysis Summary
Gemma 3 27B is Google's open-weight 27B model, with an intelligence index of 10.3 and support for vision, tool use, and function calling. The 131K context window is adequate for most business documents. Its MMLU Pro score of 0.669 reflects reasonable general knowledge, but reasoning depth and agentic reliability are limited at this scale.
For businesses, it suits lightweight content tasks, image-aware workflows, and scenarios where self-hosting or open-weight flexibility is a priority. Tool use and function calling enable basic automation, but complex multi-step agentic tasks are better handled by larger models. Its instruction-following and long-context recall scores are modest.
At $0.08 input and $0.16 output per million tokens, it is very cost-effective for an open-weight model with vision. Teams that need a deployable, multimodal model for internal tooling or cost-sensitive content pipelines will find it a practical choice, particularly where data sovereignty or self-hosting requirements apply.
Assessed June 6, 2026
Editorial notes
Gemma 3 27B from Google is an open-weight multimodal model with tool use, function calling, and vision at very low cost, though reasoning and agentic capability are limited.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Google: Gemma 3 27B compares
Google: Gemma 3 27B ranks #311 of 378 AI models we track for overall intelligence, #245 of 315 for coding, #274 of 290 for agentic tasks. Its 131K-token context window is larger than 59% of the models we list. At $0.08 per million input tokens it is cheaper than 68% of comparable models.
About Google: Gemma 3 27B
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,..
Capabilities
Architecture Detail
| Instruct Type | gemma |
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Google: Gemma 3 27B stack up?
Compare side-by-side with other professional models.
Model Information
| OpenRouter ID |
google/gemma-3-27b-it
|
| Provider | |
| Release Date | March 12, 2025 |
| Context Length | 131,072 tokens |
| Max Completion | 16,384 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.08 | $0.000080 |
| Output | $0.16 | $0.000160 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about Google: Gemma 3 27B
How much does Google: Gemma 3 27B cost?
Google: Gemma 3 27B costs $0.08 per million input tokens and $0.16 per million output tokens.
What is the context window of Google: Gemma 3 27B?
Google: Gemma 3 27B has a context window of 131,072 tokens (131K).
Is Google: Gemma 3 27B good for coding?
On our coding benchmark index, Google: Gemma 3 27B ranks #245 of 315 models, placing it in the broader range of the field for code generation and debugging.
What can Google: Gemma 3 27B do?
Google: Gemma 3 27B supports image/vision input, tool use, and function calling.
Who created Google: Gemma 3 27B?
Google: Gemma 3 27B is developed by Google and was released on March 12, 2025.
