Google model product
Gemma 2 27B
Gemma 2 27B IT is an instruction-tuned version of Google's state-of-the-art open language model.
Updated Aug 17, 2026. Default version: Gemma 2 27B
LLMBoard Score0.0Gemma 2 27B
Coverage80%16 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable
Gemma 2 27B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Gemma 2 27B Benchmark Results
Benchmark scores for Gemma 2 27B.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkARC-E | Score88.6% | Rank01 | Participants8 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkNatural Questions | Score34.5% | Rank01 | Participants7 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkBIG-Bench | Score74.9% | Rank02 | Participants3 | Percentile50.0% | EvidenceC | Evaluated |
| BenchmarkBoolQ | Score84.8% | Rank02 | Participants10 | Percentile88.9% | EvidenceC | Evaluated |
| BenchmarkTriviaQA | Score83.7% | Rank02 | Participants18 | Percentile94.1% | EvidenceC | Evaluated |
| BenchmarkPIQA | Score83.2% | Rank03 | Participants11 | Percentile80.0% | EvidenceC | Evaluated |
| BenchmarkSocial IQa | Score53.7% | Rank04 | Participants9 | Percentile62.5% | EvidenceC | Evaluated |
| BenchmarkAGIEval | Score55.1% | Rank05 | Participants10 | Percentile55.6% | EvidenceC | Evaluated |
| BenchmarkWinogrande | Score83.7% | Rank06 | Participants22 | Percentile76.2% | EvidenceC | Evaluated |
| BenchmarkHellaSwag | Score86.4% | Rank10 | Participants27 | Percentile65.4% | EvidenceC | Evaluated |
| BenchmarkARC-C | Score71.4% | Rank19 | Participants34 | Percentile45.5% | EvidenceC | Evaluated |
| BenchmarkMBPP | Score62.6% | Rank29 | Participants33 | Percentile12.5% | EvidenceC | Evaluated |
| BenchmarkGSM8k | Score74.0% | Rank42 | Participants48 | Percentile12.8% | EvidenceC | Evaluated |
| BenchmarkHumanEval | Score51.8% | Rank63 | Participants66 | Percentile4.6% | EvidenceC | Evaluated |
| BenchmarkMATH | Score42.3% | Rank65 | Participants71 | Percentile8.6% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score75.2% | Rank76 | Participants101 | Percentile25.0% | EvidenceC | Evaluated |
Gemma 2 27B Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext style control | Categoryoverall | Rank267 | Rating / score1289.2 | Votes75,754 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank273 | Rating / score1231.5 | Votes75,754 | ObservationsN/A | Result date |
Gemma 2 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 $0.65 input, $0.65 output per 1M via OpenRouter
- Tracked offerings
- 1
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderOpenRouter | Provider model IDgoogle/gemma-2-27b-it | Regionglobal | Input / 1M$0.65 | Output / 1M$0.65 | Context8.2K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Gemma 2 27B Runtime Performance
Provider-specific output speed and catalog latency for Gemma 2 27B. Runtime does not affect the capability score.
No runtime data
Browse runtime rankingsNo 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.
Gemma 2 27B Specifications
Technical details for the model's default version.
- Version
- Gemma 2 27B
- Released
- Jun 27, 2024
- Knowledge cutoff
- Unknown
- Parameters
- 27.2B
- Context window
- N/A
- Max output
- N/A
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- Gemma
Gemma 2 27B Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionGemma 2 27B | Released | LLMBoard0.0 | Parameters27.2B | ContextN/A | Max outputN/A | Open weightsNo | LicenseGemma |
Gemma 2 27B vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Gemma 2 27B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
GO
Google
Gemma 3n E2B
GOGoogle
Gemini 1.5 Flash 8B
GOGoogle
Gemma 3n E4B
GOGoogle
Gemma 3n E2B LiteRT
GOGoogle
MedGemma 4B IT
GOGoogle
Gemma 3n E4B LiteRT
What is Gemma 2 27B?
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 2026-08-17.
FAQ
Common questions about Gemma 2 27B.
When was Gemma 2 27B released?
Gemma 2 27B's default version was released on Jun 27, 2024.
How much does Gemma 2 27B cost?
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.
Who created Gemma 2 27B?
Gemma 2 27B was created by Google.
What is the context window for Gemma 2 27B?
A context window is not available for the default version.
Is Gemma 2 27B open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Gemma 2 27B?
1 provider offerings are linked to the default version.
What models should I compare Gemma 2 27B with?
Nearby ranked alternatives include Qwen2 7B, ERNIE 4.5, Phi 4 Mini.