Google model product
Gemma 2 27B
Gemma 2 27B is an instruction-tuned open language model from Google for dialogue applications.
Updated Oct 23, 2026. Default version: Gemma 2 27B
LLMBoard Score0.0Gemma 2 27B
Coverage60%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 | Score88.60% | Rank01 | Participants9 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkNatural Questions | Score34.50% | Rank01 | Participants7 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkBIG-Bench | Score74.90% | Rank02 | Participants3 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkTriviaQA | Score83.70% | Rank02 | Participants18 | Percentile94.12% | EvidenceC | Evaluated |
| BenchmarkBoolQ | Score84.80% | Rank03 | Participants11 | Percentile80.00% | EvidenceC | Evaluated |
| BenchmarkPIQA | Score83.20% | Rank04 | Participants12 | Percentile72.73% | EvidenceC | Evaluated |
| BenchmarkSocial IQa | Score53.70% | Rank04 | Participants9 | Percentile62.50% | EvidenceC | Evaluated |
| BenchmarkAGIEval | Score55.10% | Rank06 | Participants11 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkWinogrande | Score83.70% | Rank07 | Participants23 | Percentile72.73% | EvidenceC | Evaluated |
| BenchmarkHellaSwag | Score86.40% | Rank11 | Participants28 | Percentile62.96% | EvidenceC | Evaluated |
| BenchmarkARC-C | Score71.40% | Rank19 | Participants35 | Percentile47.06% | EvidenceC | Evaluated |
| BenchmarkMBPP | Score62.60% | Rank29 | Participants33 | Percentile12.50% | EvidenceC | Evaluated |
| BenchmarkGSM8k | Score74.00% | Rank42 | Participants48 | Percentile12.77% | EvidenceC | Evaluated |
| BenchmarkHumanEval | Score51.80% | Rank63 | Participants66 | Percentile4.62% | EvidenceC | Evaluated |
| BenchmarkMATH | Score42.30% | Rank65 | Participants71 | Percentile8.57% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score75.20% | Rank78 | Participants103 | Percentile24.51% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,289.55 rating | Rank195 | Participants218 | Percentile10.60% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,231.40 rating | Rank197 | Participants218 | Percentile9.68% | EvidenceA | 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 | Categorypolish | Rank129 | Rating / score1,351.16 | Votes58 | ObservationsN/A | Result date |
| Arenatext | Categorypolish | Rank148 | Rating / score1,277.17 | Votes58 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank160 | Rating / score1,229.26 | Votes1,808 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank161 | Rating / score1,175.50 | Votes1,808 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank164 | Rating / score1,237.66 | Votes1,440 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank165 | Rating / score1,173.69 | Votes1,440 | ObservationsN/A | Result date |
| Arenatext style control | Categoryfrench | Rank167 | Rating / score1,313.17 | Votes793 | ObservationsN/A | Result date |
| Arenatext | Categoryfrench | Rank172 | Rating / score1,247.65 | Votes793 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank172 | Rating / score1,269.43 | Votes2,037 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank173 | Rating / score1,292.71 | Votes11,429 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank173 | Rating / score1,293.32 | Votes845 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank176 | Rating / score1,208.99 | Votes2,037 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank177 | Rating / score1,228.20 | Votes845 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry writing and literature and language | Rank180 | Rating / score1,297.80 | Votes20,390 | ObservationsN/A | Result date |
| Arenatext style control | Categorychinese | Rank186 | Rating / score1,300.92 | Votes6,872 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank186 | Rating / score1,272.99 | Votes12,280 | ObservationsN/A | Result date |
| Arenatext | Categorycreative writing | Rank187 | Rating / score1,240.43 | Votes11,429 | ObservationsN/A | Result date |
| Arenatext style control | Categoryrussian | Rank188 | Rating / score1,291.69 | Votes9,678 | ObservationsN/A | Result date |
| Arenatext style control | Categorynon english | Rank190 | Rating / score1,274.69 | Votes34,471 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry writing and literature and language | Rank191 | Rating / score1,248.76 | Votes20,390 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry legal and government | Rank191 | Rating / score1,311.17 | Votes4,458 | ObservationsN/A | Result date |
| Arenatext style control | Categorylonger query | Rank192 | Rating / score1,300.65 | Votes9,918 | ObservationsN/A | Result date |
| Arenatext style control | Categorymulti turn | Rank192 | Rating / score1,279.59 | Votes13,588 | ObservationsN/A | Result date |
| Arenatext | Categoryrussian | Rank193 | Rating / score1,233.80 | Votes9,678 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank194 | Rating / score1,221.07 | Votes6,872 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry life and physical and social science | Rank194 | Rating / score1,303.85 | Votes12,863 | ObservationsN/A | Result date |
| Arenatext | Categorynon english | Rank195 | Rating / score1,216.96 | Votes34,471 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry mathematical | Rank195 | Rating / score1,265.89 | Votes8,869 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry medicine and healthcare | Rank195 | Rating / score1,290.78 | Votes3,862 | ObservationsN/A | Result date |
| Arenatext style control | Categoryinstruction following | Rank195 | Rating / score1,271.42 | Votes29,545 | 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
- 3
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 |
| ProviderKilo Gateway | Provider model IDgoogle/gemma-2-27b-it | Regionglobal | Input / 1M$0.65 | Output / 1M$0.65 | Context8.2K | Updated |
| ProviderAI/ML API | Provider model IDgoogle/gemma-2-27b-it | Regionglobal | Input / 1M$0.6877 | Output / 1M$0.6877 | 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
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.
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
- Yes
- 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 | LLMBoard0.00 | Parameters27.2B | ContextN/A | Max outputN/A | Open weightsYes | LicenseGemma |
Models similar to Gemma 2 27B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
GO
Google
MedGemma 4B IT
GOGoogle
Gemini 1.0 Pro
GOGoogle
Gemini 1.5 Flash 8B
GOGoogle
Gemma 2 9B
GOGoogle
Gemma 3 1B
GOGoogle
Gemma 3 4B
What is Gemma 2 27B?
Key information about Gemma 2 27B and its available data.
Gemma 2 27B is an instruction-tuned version of Google's open language model, developed using supervised fine-tuning, distillation from larger models, and RLHF. It is used for text generation tasks including question answering, summarization, and reasoning.
Data as of 2026-10-22.
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?
Yes. The default version is marked as open weight under Gemma.
How many API providers offer Gemma 2 27B?
3 provider offerings are linked to the default version.