Google model product
Gemma 3 27B
Gemma 3 27B is a 27-billion-parameter vision-language model from Google that accepts text and image input and generates text output.
Updated Sep 8, 2026. Default version: Gemma 3 27B
LLMBoard Score14.5Gemma 3 27B
Coverage100%27 benchmark families
Context window131.1KTokens
Official input priceN/AOfficial price unavailable
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.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkECLeKTic | Score16.70% | Rank02 | Participants8 | Percentile85.71% | EvidenceC | Evaluated |
| BenchmarkHiddenMath | Score60.30% | Rank02 | Participants13 | Percentile91.67% | EvidenceC | Evaluated |
| BenchmarkVQAv2 (val) | Score71.00% | Rank02 | Participants3 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkBird-SQL (dev) | Score54.40% | Rank03 | Participants9 | Percentile75.00% | EvidenceC | Evaluated |
| BenchmarkNatural2Code | Score84.50% | Rank03 | Participants8 | Percentile71.43% | EvidenceC | Evaluated |
| BenchmarkBIG-Bench Hard | Score87.60% | Rank04 | Participants21 | Percentile85.00% | EvidenceC | Evaluated |
| BenchmarkInfoVQA | Score70.60% | Rank06 | Participants10 | Percentile44.44% | EvidenceC | Evaluated |
| BenchmarkBIG-Bench Extra Hard | Score19.30% | Rank07 | Participants11 | Percentile40.00% | EvidenceC | Evaluated |
| BenchmarkFACTS Grounding | Score74.90% | Rank07 | Participants13 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkGlobal-MMLU-Lite | Score75.10% | Rank07 | Participants15 | Percentile57.14% | EvidenceC | Evaluated |
| BenchmarkMATH | Score89.00% | Rank07 | Participants71 | Percentile91.43% | EvidenceC | Evaluated |
| BenchmarkGSM8k | Score95.90% | Rank08 | Participants48 | Percentile85.11% | EvidenceC | Evaluated |
| BenchmarkMMMU (val) | Score64.90% | Rank09 | Participants13 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkIFEval | Score90.40% | Rank13 | Participants68 | Percentile82.09% | EvidenceC | Evaluated |
| BenchmarkWMT24++ | Score53.40% | Rank14 | Participants23 | Percentile40.91% | EvidenceC | Evaluated |
| BenchmarkTextVQA | Score65.10% | Rank15 | Participants16 | Percentile6.67% | EvidenceC | Evaluated |
| BenchmarkMBPP | Score74.40% | Rank19 | Participants33 | Percentile43.75% | EvidenceC | Evaluated |
| BenchmarkChartQA | Score78.00% | Rank23 | Participants26 | Percentile12.00% | EvidenceC | Evaluated |
| BenchmarkMathVista-Mini | Score67.60% | Rank23 | Participants25 | Percentile8.33% | EvidenceC | Evaluated |
| BenchmarkAI2D | Score84.50% | Rank24 | Participants34 | Percentile30.30% | EvidenceC | Evaluated |
| BenchmarkMRCR v2 (8-needle) | Score13.50% | Rank24 | Participants24 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkDocVQA | Score86.60% | Rank25 | Participants28 | Percentile11.11% | EvidenceC | Evaluated |
| BenchmarkHumanEval | Score87.80% | Rank28 | Participants66 | Percentile58.46% | EvidenceC | Evaluated |
| BenchmarkSimpleQA | Score10.00% | Rank42 | Participants47 | Percentile10.87% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score29.70% | Rank64 | Participants75 | Percentile14.86% | EvidenceC | Evaluated |
| BenchmarkLM Arena Vision | Score1,164.31 rating | Rank73 | Participants107 | Percentile32.08% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision Style Control | Score1,158.67 rating | Rank77 | Participants107 | Percentile28.30% | EvidenceA | Evaluated |
| BenchmarkMMLU-Pro | Score67.50% | Rank100 | Participants138 | Percentile27.74% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,379.21 rating | Rank112 | Participants121 | Percentile7.50% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,357.50 rating | Rank131 | Participants210 | Percentile37.80% | EvidenceA | Evaluated |
Gemma 3 27B Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision | Categorycreative writing | Rank22 | Rating / score1,182.13 | Votes732 | ObservationsN/A | Result date |
| Arenavision style control | Categorycreative writing | Rank23 | Rating / score1,174.60 | Votes732 | ObservationsN/A | Result date |
| Arenavision | Categorycaptioning | Rank26 | Rating / score1,152.68 | Votes260 | ObservationsN/A | Result date |
| Arenavision style control | Categorycaptioning | Rank28 | Rating / score1,118.57 | Votes260 | ObservationsN/A | Result date |
| Arenavision | Categoryentity recognition | Rank30 | Rating / score1,196.67 | Votes312 | ObservationsN/A | Result date |
| Arenavision style control | Categoryentity recognition | Rank33 | Rating / score1,170.24 | Votes312 | ObservationsN/A | Result date |
| Arenavision | Categoryhumor | Rank62 | Rating / score1,166.25 | Votes762 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhumor | Rank63 | Rating / score1,153.14 | Votes762 | ObservationsN/A | Result date |
| Arenavision | Categorycreative writing vision | Rank65 | Rating / score1,176.53 | Votes627 | ObservationsN/A | Result date |
| Arenavision style control | Categorycreative writing vision | Rank65 | Rating / score1,166.78 | Votes627 | ObservationsN/A | Result date |
| Arenavision style control | Categorychinese | Rank67 | Rating / score1,170.91 | Votes1,021 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank69 | Rating / score1,160.71 | Votes1,021 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank69 | Rating / score1,188.61 | Votes7,948 | ObservationsN/A | Result date |
| Arenavision | Categorydiagram | Rank71 | Rating / score1,155.71 | Votes1,719 | ObservationsN/A | Result date |
| Arenavision | Categoryocr | Rank71 | Rating / score1,156.95 | Votes6,202 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhomework | Rank72 | Rating / score1,170.41 | Votes1,032 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank73 | Rating / score1,164.31 | Votes17,003 | ObservationsN/A | Result date |
| Arenavision style control | Categoryocr | Rank73 | Rating / score1,160.95 | Votes6,202 | ObservationsN/A | Result date |
| Arenavision | Categoryhomework | Rank74 | Rating / score1,162.69 | Votes1,032 | ObservationsN/A | Result date |
| Arenavision style control | Categorydiagram | Rank75 | Rating / score1,164.67 | Votes1,719 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank75 | Rating / score1,173.51 | Votes7,948 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank77 | Rating / score1,158.67 | Votes17,003 | ObservationsN/A | Result date |
| Arenatext style control | Categorypolish | Rank108 | Rating / score1,369.20 | Votes2,818 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank110 | Rating / score1,360.60 | Votes1,205 | ObservationsN/A | Result date |
| Arenatext factuality | Categorynon english | Rank110 | Rating / score1,361.37 | Votes1,071 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry medicine and healthcare | Rank112 | Rating / score1,391.02 | Votes2,337 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryexclude ties | Rank112 | Rating / score1,352.98 | Votes1,627 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryoverall | Rank112 | Rating / score1,379.21 | Votes2,335 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank112 | Rating / score1,368.85 | Votes1,205 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank113 | Rating / score1,307.15 | Votes881 | ObservationsN/A | Result date |
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
- 5
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderOpenRouter | Provider model IDgoogle/gemma-3-27b-it | Regionglobal | Input / 1M$0.08 | Output / 1M$0.45 | Context131.1K | Updated |
| ProviderCortecs | Provider model IDgemma-3-27b-it | Regionglobal | Input / 1M$0.099 | Output / 1M$0.299 | Context131K | Updated |
| ProviderNovitaAI | Provider model IDgoogle/gemma-3-27b-it | Regionglobal | Input / 1M$0.119 | Output / 1M$0.20 | Context98.3K | Updated |
| ProviderGreenPT | Provider model IDgemma-3-27b-it | Regionglobal | Input / 1M$0.342 | Output / 1M$0.684 | Context40K | Updated |
| ProviderSTACKIT | Provider model IDgoogle/gemma-3-27b-it | Regionglobal | Input / 1M$0.53 | Output / 1M$0.76 | Context37K | Updated |
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 Runtime Performance
Provider-specific output speed and catalog latency for Gemma 3 27B. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderDeepInfra | Output Speed33.00 tok/s | Catalog Latency0.20 s | Max Input131.1K | Max Output131.1K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
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
- Yes
- License
- Gemma
Gemma 3 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 3 27B | Released | LLMBoard14.49 | Parameters27B | Context131.1K | Max output131.1K | Open weightsYes | LicenseGemma |
Models similar to Gemma 3 27B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
GO
Google
Gemini 1.5 Flash
GOGoogle
Gemma 3 12B
GOGoogle
Gemma 4 E2B
GOGoogle
Gemini 2.5 Flash Lite
GOGoogle
Gemini 1.5 Pro
GOGoogle
Gemini 2.0 Flash Lite
What is Gemma 3 27B?
Key information about Gemma 3 27B and its available data.
Gemma 3 27B is a Google vision-language model with a 128K context window, multilingual support, and open weights. It is designed for question answering, summarization, reasoning, and image understanding tasks.
Data as of 2026-09-08.
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?
Yes. The default version is marked as open weight under Gemma.
How many API providers offer Gemma 3 27B?
5 provider offerings are linked to the default version.