Google model product
Gemma 2 27B IT is an instruction-tuned version of Google's state-of-the-art open language model.
Updated Aug 12, 2026. Default version: Gemma 2 27B
Technical details for the model's default version.
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for Gemma 2 27B.
| ARC-E | 88.6% | 01 | 8 | 100.0% | C | |
| Natural Questions | 34.5% | 01 | 7 | 100.0% | C | |
| BIG-Bench | 74.9% | 02 | 3 | 50.0% | C | |
| BoolQ | 84.8% | 02 | 10 | 88.9% | C | |
| TriviaQA | 83.7% | 02 | 18 | 94.1% | C | |
| PIQA | 83.2% | 03 | 11 | 80.0% | C | |
| Social IQa | 53.7% | 04 | 9 | 62.5% | C | |
| AGIEval | 55.1% | 05 | 10 | 55.6% | C | |
| Winogrande | 83.7% | 06 | 22 | 76.2% | C | |
| HellaSwag | 86.4% | 10 | 27 | 65.4% | C | |
| ARC-C | 71.4% | 19 | 34 | 45.5% | C | |
| MBPP | 62.6% | 29 | 33 | 12.5% | C | |
| GSM8k | 74.0% | 42 | 48 | 12.8% | C | |
| HumanEval | 51.8% | 63 | 66 | 4.6% | C | |
| MATH | 42.3% | 65 | 71 | 8.6% | C | |
| MMLU | 75.2% | 76 | 100 | 24.2% | C |
Preference and agent-evaluation results for the default version.
| text style control | overall | 264 | 1289.2 | 75,754 | N/A | |
| text | overall | 270 | 1231.5 | 75,754 | N/A |
Provider-specific output speed and catalog latency for Gemma 2 27B. Runtime does not affect the capability score.
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Official vendor API pricing appears first, followed by individual provider offers.
| OpenRouter | google/gemma-2-27b-it | global | $0.65 | $0.65 | 8.2K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Available versions of this model. The score column identifies the version used in the overall ranking.
| Gemma 2 27B | 0.0 | 27.2B | N/A | N/A | No | Gemma |
Key information about Gemma 2 27B and its available data.
Gemma 2 27B IT is an instruction-tuned version of Google's state-of-the-art open language model. Built from the same research and technology as Gemini, it's optimized for dialogue applications through supervised fine-tuning, distillation from larger models, and RLHF.
The model excels at text generation tasks including question answering, summarization, and reasoning.
Data as of 2026-08-11.
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Common questions about Gemma 2 27B.
Gemma 2 27B's default version was released on Jun 27, 2024.
No official standard PAYG price is currently available for Gemma 2 27B. The lowest tracked third-party offer starts at $0.65 input and $0.65 output via OpenRouter.
Gemma 2 27B was created by Google.
A context window is not available for the default version.
No. The default version is not marked as having publicly available weights.
1 provider offerings are linked to the default version.
Nearby ranked alternatives include Jamba 1.5 Large, Codestral 22B, Grok 1.5V.