Gemma 3 27B
Lightweight model with vision-language input, multilingual support, visual reasoning, and top-tier performance per size.
About model
Gemma 3 27B generates human-like text based on input prompts, excelling at conversational dialogue and content creation. It is suitable for developers and businesses requiring advanced language generation capabilities.
Performance benchmarks
Model | AIME 2025 | GPQA Diamond | HLE | LiveCodeBench | MATH500 | SWE-bench verified |
|---|---|---|---|---|---|---|
Gemma 3 27B | 48.9% | Related open-source models | Competitor closed-source models | |||
 Claude Opus 4.6 | 90.5% | 34.2% | 78.7% | |||
 OpenAI o3 | 83.3% | 24.9% | 99.2% | 62.3% | ||
OpenAI o1 | 76.8% | 96.4% | 48.9% | |||
GPT-4o | 49.2% | 2.7% | 32.3% | 89.3% | 31.0% |
Related models
- TypeChatCodeVision
- Main use casesSmall & FastVision
- Fine tuningSupported
- DeploymentOn-Demand DedicatedMonthly Reserved
- Parameters27B
- Context length64K
- Input modalitiesTextImage
- Output modalitiesText
- ReleasedMarch 1, 2025
- Last updatedSeptember 9, 2025
- External link
- CategoryChat