Google model product
Gemma 3 12B
Gemma 3 12B is a 12-billion-parameter vision-language model from Google that accepts text and image input and generates text output.
Updated Oct 23, 2026. Default version: Gemma 3 12B
LLMBoard Score9.0Gemma 3 12B
Coverage100%26 benchmark families
Context window131.1KTokens
Official input priceN/AOfficial price unavailable
Gemma 3 12B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Gemma 3 12B Benchmark Results
Benchmark scores for Gemma 3 12B.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkVQAv2 (val) | Score71.60% | Rank01 | Participants3 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkECLeKTic | Score10.30% | Rank03 | Participants8 | Percentile71.43% | EvidenceC | Evaluated |
| BenchmarkBird-SQL (dev) | Score47.90% | Rank04 | Participants9 | Percentile62.50% | EvidenceC | Evaluated |
| BenchmarkHiddenMath | Score54.50% | Rank04 | Participants13 | Percentile75.00% | EvidenceC | Evaluated |
| BenchmarkNatural2Code | Score80.70% | Rank04 | Participants8 | Percentile57.14% | EvidenceC | Evaluated |
| BenchmarkBIG-Bench Hard | Score85.70% | Rank06 | Participants21 | Percentile75.00% | EvidenceC | Evaluated |
| BenchmarkFACTS Grounding | Score75.80% | Rank06 | Participants13 | Percentile58.33% | EvidenceC | Evaluated |
| BenchmarkBIG-Bench Extra Hard | Score16.30% | Rank08 | Participants11 | Percentile30.00% | EvidenceC | Evaluated |
| BenchmarkGlobal-MMLU-Lite | Score69.50% | Rank09 | Participants16 | Percentile46.67% | EvidenceC | Evaluated |
| BenchmarkInfoVQA | Score64.90% | Rank09 | Participants10 | Percentile11.11% | EvidenceC | Evaluated |
| BenchmarkMMMU (val) | Score59.60% | Rank10 | Participants13 | Percentile25.00% | EvidenceC | Evaluated |
| BenchmarkMATH | Score83.80% | Rank14 | Participants71 | Percentile81.43% | EvidenceC | Evaluated |
| BenchmarkTextVQA | Score67.70% | Rank14 | Participants16 | Percentile13.33% | EvidenceC | Evaluated |
| BenchmarkGSM8k | Score94.40% | Rank16 | Participants48 | Percentile68.09% | EvidenceC | Evaluated |
| BenchmarkWMT24++ | Score51.60% | Rank16 | Participants24 | Percentile34.78% | EvidenceC | Evaluated |
| BenchmarkMBPP | Score73.00% | Rank21 | Participants33 | Percentile37.50% | EvidenceC | Evaluated |
| BenchmarkDocVQA | Score87.10% | Rank24 | Participants28 | Percentile14.81% | EvidenceC | Evaluated |
| BenchmarkIFEval | Score88.90% | Rank24 | Participants70 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkChartQA | Score75.70% | Rank25 | Participants26 | Percentile4.00% | EvidenceC | Evaluated |
| BenchmarkMathVista-Mini | Score62.90% | Rank25 | Participants26 | Percentile4.00% | EvidenceC | Evaluated |
| BenchmarkAI2D | Score84.20% | Rank26 | Participants35 | Percentile26.47% | EvidenceC | Evaluated |
| BenchmarkHumanEval | Score85.40% | Rank34 | Participants66 | Percentile49.23% | EvidenceC | Evaluated |
| BenchmarkSimpleQA | Score6.30% | Rank43 | Participants47 | Percentile8.70% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score24.60% | Rank68 | Participants76 | Percentile10.67% | EvidenceC | Evaluated |
| BenchmarkAA AIME 2025 | Score18.33% | Rank81 | Participants96 | Percentile15.79% | EvidenceB | EvaluatedN/A |
| BenchmarkAA SciCode Subtasks | Score16.44% | Rank87 | Participants89 | Percentile2.27% | EvidenceB | EvaluatedN/A |
| BenchmarkMMLU-Pro | Score60.60% | Rank114 | Participants142 | Percentile19.86% | EvidenceC | Evaluated |
| BenchmarkAA IFBench | Score36.73% | Rank130 | Participants168 | Percentile22.75% | EvidenceB | EvaluatedN/A |
| BenchmarkAA CritPt | Score0.00% | Rank141 | Participants200 | Percentile29.65% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Text | Score1,334.25 rating | Rank154 | Participants218 | Percentile29.49% | EvidenceA | Evaluated |
Gemma 3 12B Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext | Categorygerman | Rank114 | Rating / score1,370.38 | Votes166 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank121 | Rating / score1,371.67 | Votes166 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry business and management and financial operations | Rank123 | Rating / score1,376.42 | Votes364 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry legal and government | Rank127 | Rating / score1,380.71 | Votes217 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry business and management and financial operations | Rank130 | Rating / score1,386.82 | Votes364 | ObservationsN/A | Result date |
| Arenatext | Categorycreative writing | Rank135 | Rating / score1,331.13 | Votes600 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank141 | Rating / score1,332.56 | Votes600 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry legal and government | Rank141 | Rating / score1,382.80 | Votes217 | ObservationsN/A | Result date |
| Arenatext style control | Categoryrussian | Rank141 | Rating / score1,357.43 | Votes285 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry life and physical and social science | Rank143 | Rating / score1,365.86 | Votes760 | ObservationsN/A | Result date |
| Arenatext | Categoryrussian | Rank144 | Rating / score1,335.29 | Votes285 | ObservationsN/A | Result date |
| Arenatext | Categorynon english | Rank150 | Rating / score1,317.93 | Votes1,499 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry life and physical and social science | Rank151 | Rating / score1,368.80 | Votes760 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry entertainment and sports and media | Rank153 | Rating / score1,297.44 | Votes697 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry writing and literature and language | Rank153 | Rating / score1,307.12 | Votes1,010 | ObservationsN/A | Result date |
| Arenatext style control | Categorynon english | Rank153 | Rating / score1,335.55 | Votes1,499 | ObservationsN/A | Result date |
| Arenatext | Categoryexclude ties | Rank154 | Rating / score1,289.09 | Votes2,526 | ObservationsN/A | Result date |
| Arenatext | Categorymulti turn | Rank154 | Rating / score1,333.75 | Votes471 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank154 | Rating / score1,334.25 | Votes3,829 | ObservationsN/A | Result date |
| Arenatext style control | Categorymulti turn | Rank154 | Rating / score1,344.30 | Votes471 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry mathematical | Rank155 | Rating / score1,335.93 | Votes333 | ObservationsN/A | Result date |
| Arenatext style control | Categorylonger query | Rank156 | Rating / score1,346.54 | Votes371 | ObservationsN/A | Result date |
| Arenatext | Categoryenglish | Rank157 | Rating / score1,348.51 | Votes2,330 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry mathematical | Rank157 | Rating / score1,349.24 | Votes333 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry medicine and healthcare | Rank158 | Rating / score1,334.26 | Votes155 | ObservationsN/A | Result date |
| Arenatext | Categorylonger query | Rank158 | Rating / score1,316.79 | Votes371 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank159 | Rating / score1,305.60 | Votes697 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexclude ties | Rank162 | Rating / score1,295.74 | Votes2,526 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank162 | Rating / score1,341.80 | Votes3,829 | ObservationsN/A | Result date |
| Arenatext | Categoryinstruction following | Rank163 | Rating / score1,299.15 | Votes1,145 | ObservationsN/A | Result date |
Gemma 3 12B Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $0.04 input, $0.12 output per 1M via Kilo Gateway
- Tracked offerings
- 10
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderNvidia | Provider model IDgoogle/gemma-3-12b-it | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context131.1K | Updated |
| ProviderKilo Gateway | Provider model IDgoogle/gemma-3-12b-it | Regionglobal | Input / 1M$0.04 | Output / 1M$0.12 | Context131.1K | Updated |
| ProviderOpenRouter | Provider model IDgoogle/gemma-3-12b-it | Regionglobal | Input / 1M$0.05 | Output / 1M$0.15 | Context131.1K | Updated |
| ProviderHelicone | Provider model IDgemma-3-12b-it | Regionglobal | Input / 1M$0.05 | Output / 1M$0.10 | Context131.1K | Updated |
| ProviderNovita AI | Provider model IDgoogle/gemma-3-12b-it | Regionglobal | Input / 1M$0.05 | Output / 1M$0.10 | Context131.1K | Updated |
| ProviderHugging Face | Provider model IDgoogle/gemma-3-12b-it | Regionglobal | Input / 1M$0.05 | Output / 1M$0.15 | Context131.1K | Updated |
| ProviderDeep Infra | Provider model IDgoogle/gemma-3-12b-it | Regionglobal | Input / 1M$0.05 | Output / 1M$0.15 | Context131.1K | Updated |
| ProviderAI/ML API | Provider model IDgoogle/gemma-3-12b-it | Regionglobal | Input / 1M$0.0529 | Output / 1M$0.1587 | Context131K | Updated |
| ProviderMerge Gateway | Provider model IDgoogle/gemma-3-12b-it | Regionglobal | Input / 1M$0.09 | Output / 1M$0.29 | Context128K | Updated |
| ProviderNeon | Provider model IDgemma-3-12b | Regionglobal | Input / 1M$0.15 | Output / 1M$0.50 | Context131.1K | 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 12B Runtime Performance
Provider-specific output speed and catalog latency for Gemma 3 12B. 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 3 12B Specifications
Technical details for the model's default version.
- Version
- Gemma 3 12B
- Released
- Mar 12, 2025
- Knowledge cutoff
- Unknown
- Parameters
- 12B
- Context window
- 131.1K
- Max output
- 131.1K
- Inputs
- image, text
- Outputs
- text
- Open weights
- Yes
- License
- Gemma
Gemma 3 12B 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 12B | Released | LLMBoard9.04 | Parameters12B | Context131.1K | Max output131.1K | Open weightsYes | LicenseGemma |
Models similar to Gemma 3 12B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
GO
Google
Gemini 1.5 Flash
GOGoogle
Gemma 4 E2B
GOGoogle
Gemma 3 27B
GOGoogle
Gemini Diffusion
GOGoogle
MedGemma 4B IT
GOGoogle
Gemini 1.0 Pro
What is Gemma 3 12B?
Key information about Gemma 3 12B and its available data.
Gemma 3 12B is a 12-billion-parameter vision-language model from Google with a 128K context window, multilingual support, and open weights. It is used for question answering, summarization, reasoning, and image understanding.
Data as of 2026-10-22.
FAQ
Common questions about Gemma 3 12B.
When was Gemma 3 12B released?
Gemma 3 12B's default version was released on Mar 12, 2025.
How much does Gemma 3 12B cost?
No official standard PAYG price is currently available for Gemma 3 12B. The lowest tracked third-party offer starts at $0.04 input and $0.12 output via Kilo Gateway.
Who created Gemma 3 12B?
Gemma 3 12B was created by Google.
What is the context window for Gemma 3 12B?
The default version has a 131.1K token context window.
Is Gemma 3 12B open weight?
Yes. The default version is marked as open weight under Gemma.
How many API providers offer Gemma 3 12B?
10 provider offerings are linked to the default version.