Google model product
Gemma 4 12B
95 billion parameters and a 256K context window.
Updated Sep 8, 2026. Default version: Gemma 4 12B
LLMBoard Score36.9Gemma 4 12B
Coverage40%15 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable
Gemma 4 12B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Gemma 4 12B Benchmark Results
Benchmark scores for Gemma 4 12B.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkBIG-Bench Extra Hard | Score53.00% | Rank03 | Participants11 | Percentile80.00% | EvidenceC | Evaluated |
| BenchmarkCoVoST2 | Score38.50% | Rank03 | Participants4 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkFLEURS | Score93.10% | Rank04 | Participants6 | Percentile40.00% | EvidenceC | Evaluated |
| BenchmarkMedXpertQA | Score48.70% | Rank08 | Participants12 | Percentile36.36% | EvidenceC | Evaluated |
| BenchmarkMRCR v2 (8-needle) | Score43.40% | Rank12 | Participants24 | Percentile52.17% | EvidenceC | Evaluated |
| BenchmarkCodeForces | Score55.30% | Rank16 | Participants17 | Percentile6.25% | EvidenceC | Evaluated |
| BenchmarkMathVision | Score79.70% | Rank16 | Participants35 | Percentile55.88% | EvidenceC | Evaluated |
| BenchmarkOmniDocBench 1.5 | Score16.40% | Rank16 | Participants18 | Percentile11.76% | EvidenceC | Evaluated |
| BenchmarkAIME 2026 | Score77.50% | Rank19 | Participants22 | Percentile14.29% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench v6 | Score72.00% | Rank33 | Participants62 | Percentile47.54% | EvidenceC | Evaluated |
| BenchmarkMMMLU | Score83.40% | Rank35 | Participants49 | Percentile29.17% | EvidenceC | Evaluated |
| BenchmarkMMMU-Pro | Score69.10% | Rank39 | Participants69 | Percentile44.12% | EvidenceC | Evaluated |
| BenchmarkMMLU-Pro | Score77.20% | Rank71 | Participants138 | Percentile48.91% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score5.20% | Rank99 | Participants103 | Percentile3.92% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score78.80% | Rank102 | Participants247 | Percentile58.94% | EvidenceC | Evaluated |
Gemma 4 12B Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
Gemma 4 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 $0.05 input, $0.25 output per 1M via NanoGPT
- Tracked offerings
- 1
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderNanoGPT | Provider model IDgemma-4-12b-it | Regionglobal | Input / 1M$0.05 | Output / 1M$0.25 | Context262.1K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Gemma 4 12B Runtime Performance
Provider-specific output speed and catalog latency for Gemma 4 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 4 12B Specifications
Technical details for the model's default version.
- Version
- Gemma 4 12B
- Released
- May 23, 2026
- Knowledge cutoff
- Jan 1, 2025
- Parameters
- 12B
- Context window
- N/A
- Max output
- N/A
- Inputs
- image, text
- Outputs
- text
- Open weights
- Yes
- License
- Apache 2.0
Gemma 4 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 4 12B | Released | LLMBoard36.90 | Parameters12B | ContextN/A | Max outputN/A | Open weightsYes | LicenseApache 2.0 |
Models similar to Gemma 4 12B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
GO
Google
Gemini 2.5 Flash
GOGoogle
DiffusionGemma 26B A4B
GOGoogle
Gemini 2.0 Flash Thinking
GOGoogle
Gemini 2.0 Flash
GOGoogle
Gemini 2.5 Pro
GOGoogle
Gemini 3.1 Flash Lite
What is Gemma 4 12B?
Key information about Gemma 4 12B and its available data.
Gemma 4 12B is an encoder-free, decoder-only transformer that accepts text, image, audio, and video inputs and produces text output. 95 billion parameters.
Data as of 2026-09-08.
FAQ
Common questions about Gemma 4 12B.
When was Gemma 4 12B released?
Gemma 4 12B's default version was released on May 23, 2026.
How much does Gemma 4 12B cost?
No official standard PAYG price is currently available for Gemma 4 12B. The lowest tracked third-party offer starts at $0.05 input and $0.25 output via NanoGPT.
Who created Gemma 4 12B?
Gemma 4 12B was created by Google.
What is the context window for Gemma 4 12B?
A context window is not available for the default version.
Is Gemma 4 12B open weight?
Yes. The default version is marked as open weight under Apache 2.0.
How many API providers offer Gemma 4 12B?
1 provider offerings are linked to the default version.