Google model product
Gemma 3 27B
Gemma 3 27B is a 27-billion-parameter vision-language model from Google, handling text and image input and generating text output.
Updated Aug 12, 2026. Default version: Gemma 3 27B
LLMBoard score15.8Gemma 3 27B
Coverage100%27 benchmark families
Context window131.1KTokens
Official input priceN/AOfficial price unavailable
Gemma 3 27B Specifications
Technical details for the model's default version.
- Version
- Gemma 3 27B
- Released
- Mar 12, 2025
- Knowledge cutoff
- Unknown
- Parameters
- 27B
- Context window
- 131.1K
- Max output
- 131.1K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Gemma
Gemma 3 27B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Gemma 3 27B Benchmark Results
Benchmark scores for Gemma 3 27B.
| ECLeKTic | 16.7% | 02 | 8 | 85.7% | C | |
| HiddenMath | 60.3% | 02 | 13 | 91.7% | C | |
| VQAv2 (val) | 71.0% | 02 | 3 | 50.0% | C | |
| Bird-SQL (dev) | 54.4% | 03 | 7 | 66.7% | C | |
| Natural2Code | 84.5% | 03 | 8 | 71.4% | C | |
| BIG-Bench Hard | 87.6% | 04 | 21 | 85.0% | C | |
| Global-MMLU-Lite | 75.1% | 06 | 14 | 61.5% | C | |
| InfoVQA | 70.6% | 06 | 9 | 37.5% | C | |
| BIG-Bench Extra Hard | 19.3% | 07 | 11 | 40.0% | C | |
| FACTS Grounding | 74.9% | 07 | 13 | 50.0% | C | |
| MATH | 89.0% | 07 | 71 | 91.4% | C | |
| GSM8k | 95.9% | 08 | 48 | 85.1% | C | |
| MMMU (val) | 64.9% | 09 | 11 | 20.0% | C | |
| IFEval | 90.4% | 13 | 65 | 81.3% | C | |
| TextVQA | 65.1% | 14 | 15 | 7.1% | C | |
| WMT24++ | 53.4% | 14 | 23 | 40.9% | C | |
| MBPP | 74.4% | 19 | 33 | 43.8% | C | |
| ChartQA | 78.0% | 21 | 24 | 13.0% | C | |
| MathVista-Mini | 67.6% | 21 | 23 | 9.1% | C | |
| MRCR v2 (8-needle) | 13.5% | 21 | 21 | 0.0% | C | |
| AI2D | 84.5% | 23 | 32 | 29.0% | C | |
| DocVQA | 86.6% | 23 | 26 | 12.0% | C | |
| HumanEval | 87.8% | 28 | 66 | 58.5% | C | |
| SimpleQA | 10.0% | 41 | 46 | 11.1% | C | |
| LiveCodeBench | 29.7% | 62 | 73 | 15.3% | C | |
| MMLU-Pro | 67.5% | 92 | 129 | 28.9% | C | |
| GPQA | 42.4% | 198 | 234 | 15.4% | C |
Gemma 3 27B Arena Results
Preference and agent-evaluation results for the default version.
| vision | overall | 91 | 1165.3 | 17,179 | N/A | |
| vision style control | overall | 91 | 1159.7 | 17,179 | N/A | |
| text factuality | overall | 139 | 1381.1 | 2,401 | N/A | |
| text | overall | 172 | 1358.2 | 47,584 | N/A | |
| text style control | overall | 176 | 1365.8 | 47,584 | N/A |
Gemma 3 27B Runtime Performance
Provider-specific output speed and catalog latency for Gemma 3 27B. Runtime does not affect the capability score.
| DeepInfra | 33 tok/s | 0.2 s | 131.1K | 131.1K | |
| Novita | 33 tok/s | 0.2 s | 131.1K | 131.1K |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Gemma 3 27B Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $0.08 input, $0.45 output per 1M via OpenRouter
- Tracked offerings
- 6
| OpenRouter | google/gemma-3-27b-it | global | $0.08 | $0.45 | 262.1K | |
| Cortecs | gemma-3-27b-it | global | $0.099 | $0.299 | 131K | |
| LLM Gateway | gemma-3-27b | global | $0.10 | $0.30 | 110K | |
| NovitaAI | google/gemma-3-27b-it | global | $0.119 | $0.20 | 98.3K | |
| GreenPT | gemma-3-27b-it | global | $0.342 | $0.684 | 40K | |
| STACKIT | google/gemma-3-27b-it | global | $0.53 | $0.76 | 37K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Gemma 3 27B Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| Gemma 3 27B | 15.8 | 27B | 131.1K | 131.1K | No | Gemma |
What is Gemma 3 27B?
Key information about Gemma 3 27B and its available data.
Gemma 3 27B is a 27-billion-parameter vision-language model from Google, handling text and image input and generating text output. It features a 128K context window, multilingual support, and open weights. Suitable for complex question answering, summarization, reasoning, and image understanding tasks.
Data as of 2026-08-11.
Gemma 3 27B vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Gemma 3 27B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
GO
Google
Gemini 2.5 Flash Lite
GOGoogle
Gemma 4 E2B
GOGoogle
Gemma 3 12B
GOGoogle
Gemini 1.5 Pro
GOGoogle
Gemini 1.5 Flash
GOGoogle
Gemini 2.0 Flash Lite
FAQ
Common questions about Gemma 3 27B.
When was Gemma 3 27B released?
Gemma 3 27B's default version was released on Mar 12, 2025.
How much does Gemma 3 27B cost?
No official standard PAYG price is currently available for Gemma 3 27B. The lowest tracked third-party offer starts at $0.08 input and $0.45 output via OpenRouter.
Who created Gemma 3 27B?
Gemma 3 27B was created by Google.
What is the context window for Gemma 3 27B?
The default version has a 131.1K token context window.
Is Gemma 3 27B open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Gemma 3 27B?
6 provider offerings are linked to the default version.
What models should I compare Gemma 3 27B with?
Nearby ranked alternatives include Grok 2 mini, Mistral Small 3.2 24B, Mistral Large 3.