Google model product
Gemma 4 31B is a Google dense multimodal model with 31 billion parameters and a 256K context window.
Updated Oct 23, 2026. Default version: Gemma 4 31B
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for Gemma 4 31B.
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkBIG-Bench Extra Hard | Score74.40% | Rank01 | Participants11 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMedXpertQA | Score61.30% | Rank05 | Participants12 | Percentile63.64% | EvidenceC | Evaluated |
| Benchmarkt2-bench | Score86.40% | Rank05 | Participants23 | Percentile81.82% | EvidenceC | Evaluated |
| BenchmarkMRCR v2 (8-needle) | Score66.40% | Rank08 | Participants25 | Percentile70.83% | EvidenceC | Evaluated |
| BenchmarkMathVision | Score85.60% | Rank12 | Participants38 | Percentile70.27% | EvidenceC | Evaluated |
| BenchmarkMMMLU | Score88.40% | Rank18 | Participants51 | Percentile66.00% | EvidenceC | Evaluated |
| BenchmarkMMLU-Pro | Score85.20% | Rank19 | Participants142 | Percentile87.23% | EvidenceC | Evaluated |
| BenchmarkAIME 2026 | Score89.20% | Rank20 | Participants27 | Percentile26.92% | EvidenceC | Evaluated |
| BenchmarkAA IFBench | Score75.58% | Rank21 | Participants168 | Percentile88.02% | EvidenceB | EvaluatedN/A |
| BenchmarkMMMU-Pro | Score76.90% | Rank25 | Participants73 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench v6 | Score80.00% | Rank29 | Participants67 | Percentile57.58% | EvidenceC | Evaluated |
| BenchmarkLM Arena Document Style Control | Score1,444.51 rating | Rank29 | Participants38 | Percentile24.32% | EvidenceA | Evaluated |
| BenchmarkLM Arena Document | Score1,424.51 rating | Rank30 | Participants38 | Percentile21.62% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision | Score1,276.47 rating | Rank30 | Participants113 | Percentile74.11% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision Style Control | Score1,261.85 rating | Rank35 | Participants113 | Percentile69.64% | EvidenceA | Evaluated |
| BenchmarkAA SciCode Subtasks | Score45.49% | Rank45 | Participants89 | Percentile50.00% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Text | Score1,442.73 rating | Rank51 | Participants218 | Percentile76.96% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,449.21 rating | Rank51 | Participants131 | Percentile61.54% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,452.10 rating | Rank55 | Participants218 | Percentile75.12% | EvidenceA | Evaluated |
| BenchmarkHumanity's Last Exam | Score26.50% | Rank60 | Participants109 | Percentile45.37% | EvidenceC | Evaluated |
| BenchmarkAA GPQA Diamond | Score85.66% | Rank64 | Participants199 | Percentile68.18% | EvidenceB | EvaluatedN/A |
| BenchmarkGPQA | Score84.30% | Rank74 | Participants256 | Percentile71.37% | EvidenceC | Evaluated |
| BenchmarkAA HLE Text No Tools | Score23.63% | Rank75 | Participants200 | Percentile62.81% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Webdev | Score1,367.44 rating | Rank79 | Participants107 | Percentile26.42% | EvidenceA | Evaluated |
| BenchmarkAA CritPt | Score1.43% | Rank85 | Participants200 | Percentile57.79% | EvidenceB | EvaluatedN/A |
| BenchmarkAA LCR v1.1 | Score69.67% | Rank91 | Participants193 | Percentile53.13% | EvidenceB | EvaluatedN/A |
| BenchmarkAA Omniscience Accuracy | Score20.03% | Rank126 | Participants201 | Percentile37.50% | EvidenceB | EvaluatedN/A |
Preference and agent-evaluation results for the default version.
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision | Categorycaptioning | Rank16 | Rating / score1,217.52 | Votes106 | ObservationsN/A | Result date |
| Arenavision | Categorycreative writing vision | Rank20 | Rating / score1,284.73 | Votes2,703 | ObservationsN/A | Result date |
| Arenavision | Categoryentity recognition | Rank24 | Rating / score1,225.71 | Votes359 | ObservationsN/A | Result date |
| Arenavision | Categoryhumor | Rank24 | Rating / score1,279.94 | Votes1,659 | ObservationsN/A | Result date |
| Arenavision style control | Categorycaptioning | Rank24 | Rating / score1,170.08 | Votes106 | ObservationsN/A | Result date |
| Arenavision style control | Categorycreative writing vision | Rank24 | Rating / score1,264.55 | Votes2,703 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhomework | Rank24 | Rating / score1,303.82 | Votes6,435 | ObservationsN/A | Result date |
| Arenavision | Categoryhomework | Rank25 | Rating / score1,309.71 | Votes6,435 | ObservationsN/A | Result date |
| Arenavision style control | Categoryentity recognition | Rank26 | Rating / score1,196.20 | Votes359 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhumor | Rank28 | Rating / score1,259.58 | Votes1,659 | ObservationsN/A | Result date |
| Arenadocument style control | Categoryoverall | Rank29 | Rating / score1,444.51 | Votes12,326 | ObservationsN/A | Result date |
| Arenadocument | Categoryoverall | Rank30 | Rating / score1,424.51 | Votes12,326 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank30 | Rating / score1,325.85 | Votes2,734 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank30 | Rating / score1,276.47 | Votes40,219 | ObservationsN/A | Result date |
| Arenavision style control | Categorychinese | Rank30 | Rating / score1,305.45 | Votes2,734 | ObservationsN/A | Result date |
| Arenatext | Categoryrussian | Rank31 | Rating / score1,459.68 | Votes824 | ObservationsN/A | Result date |
| Arenavision | Categoryocr | Rank33 | Rating / score1,281.94 | Votes28,054 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexpert | Rank34 | Rating / score1,497.92 | Votes501 | ObservationsN/A | Result date |
| Arenatext style control | Categoryrussian | Rank35 | Rating / score1,467.36 | Votes824 | ObservationsN/A | Result date |
| Arenavision style control | Categoryocr | Rank35 | Rating / score1,273.46 | Votes28,054 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank35 | Rating / score1,261.85 | Votes40,219 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank36 | Rating / score1,270.96 | Votes15,807 | ObservationsN/A | Result date |
| Arenavision style control | Categorydiagram | Rank37 | Rating / score1,282.89 | Votes10,238 | ObservationsN/A | Result date |
| Arenavision | Categorydiagram | Rank38 | Rating / score1,282.52 | Votes10,238 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank38 | Rating / score1,256.16 | Votes15,807 | ObservationsN/A | Result date |
| Arenatext | Categorymath | Rank44 | Rating / score1,462.65 | Votes428 | ObservationsN/A | Result date |
| Arenatext style control | Categoryinstruction following | Rank44 | Rating / score1,453.57 | Votes1,798 | ObservationsN/A | Result date |
| Arenatext style control | Categorylonger query | Rank44 | Rating / score1,470.07 | Votes1,797 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry writing and literature and language | Rank45 | Rating / score1,431.68 | Votes1,421 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry mathematical | Rank46 | Rating / score1,465.02 | Votes345 | ObservationsN/A | Result date |
Official vendor API pricing appears first, followed by individual provider offers.
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderNvidia | Provider model IDgoogle/gemma-4-31b-it | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context256K | Updated |
| ProviderRequesty | Provider model IDgemma-4-31b-it | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context262.1K | Updated |
| ProviderPoe | Provider model IDgoogle/gemma-4-31b | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context262.1K | Updated |
| ProviderAMD | Provider model IDGemma-4-31B-IT | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context262.1K | Updated |
| ProviderFastRouter | Provider model IDgoogle/gemma-4-31b-it | Regionglobal | Input / 1M$0.10 | Output / 1M$0.30 | Context262.1K | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDgemma-4-31b-it | Regionglobal | Input / 1M$0.10 | Output / 1M$0.25 | Context262.1K | Updated |
| ProviderKilo Gateway | Provider model IDgoogle/gemma-4-31b-it | Regionglobal | Input / 1M$0.10 | Output / 1M$0.34 | Context262.1K | Updated |
| ProviderCoreWeave | Provider model IDgoogle/gemma-4-31B-it | Regionglobal | Input / 1M$0.10 | Output / 1M$0.34 | Context262.1K | Updated |
| ProviderKenari | Provider model IDgemma-4-31b-it | Regionglobal | Input / 1M$0.1029 | Output / 1M$0.4057 | Context262.1K | Updated |
| ProviderLilac | Provider model IDgoogle/gemma-4-31b-it | Regionglobal | Input / 1M$0.11 | Output / 1M$0.35 | Context262.1K | Updated |
| ProviderOrcaRouter | Provider model IDgoogle/gemma-4-31b-it | Regionglobal | Input / 1M$0.13 | Output / 1M$0.38 | Context262.1K | Updated |
| ProviderNanoGPT | Provider model IDgoogle/gemma-4-31b-it | Regionglobal | Input / 1M$0.14 | Output / 1M$0.40 | Context262.1K | Updated |
| ProviderHugging Face | Provider model IDgoogle/gemma-4-31B-it | Regionglobal | Input / 1M$0.14 | Output / 1M$0.40 | Context262.1K | Updated |
| ProviderCrusoe | Provider model IDgoogle/gemma-4-31b-it | Regionglobal | Input / 1M$0.14 | Output / 1M$0.40 | Context262.1K | Updated |
| ProviderMerge Gateway | Provider model IDgoogle/gemma-4-31b-it | Regionglobal | Input / 1M$0.14 | Output / 1M$0.40 | Context262.1K | Updated |
| ProviderOllama Cloud | Provider model IDgemma4:31b | Regionglobal | Input / 1M$0.14 | Output / 1M$0.40 | Context262.1K | Updated |
| ProviderFriendli | Provider model IDgoogle/gemma-4-31B-it | Regionglobal | Input / 1M$0.14 | Output / 1M$0.40 | Context262.1K | Updated |
| ProviderVercel AI Gateway | Provider model IDgoogle/gemma-4-31b-it | Regionglobal | Input / 1M$0.14 | Output / 1M$0.40 | Context262.1K | Updated |
| ProviderNovita AI | Provider model IDgoogle/gemma-4-31b-it | Regionglobal | Input / 1M$0.14 | Output / 1M$0.40 | Context262.1K | Updated |
| ProviderAbacus | Provider model IDgoogle/gemma-4-31b-it | Regionglobal | Input / 1M$0.14 | Output / 1M$0.40 | Context262.1K | Updated |
| ProviderNeuralwatt | Provider model IDgemma-4-31b | Regionglobal | Input / 1M$0.144 | Output / 1M$0.42 | Context262.1K | Updated |
| ProviderDigitalOcean | Provider model IDgemma-4-31B-it | Regionglobal | Input / 1M$0.18 | Output / 1M$0.50 | Context256K | Updated |
| ProviderDeep Infra | Provider model IDgoogle/gemma-4-31B-it | Regionglobal | Input / 1M$0.20 | Output / 1M$0.40 | Context262.1K | Updated |
| ProviderOpenRouter | Provider model IDgoogle/gemma-4-31b-it | Regionglobal | Input / 1M$0.20 | Output / 1M$0.40 | Context262.1K | Updated |
| Providerai& | Provider model IDgoogle/gemma-4-31b-it | Regionglobal | Input / 1M$0.20 | Output / 1M$0.50 | Context262.1K | Updated |
| ProviderCortecs | Provider model IDgemma-4-31b-it | Regionglobal | Input / 1M$0.223 | Output / 1M$0.39 | Context262K | Updated |
| ProviderInfomaniak | Provider model IDgoogle/gemma-4-31B-it | Regionglobal | Input / 1M$0.25 | Output / 1M$0.50 | Context100K | Updated |
| ProviderBerget.AI | Provider model IDgoogle/gemma-4-31B-it | Regionglobal | Input / 1M$0.2804 | Output / 1M$0.5608 | Context128K | Updated |
| ProviderSambaNova | Provider model IDgemma-4-31B-it | Regionglobal | Input / 1M$0.38 | Output / 1M$1.15 | Context131.1K | Updated |
| ProviderNanoGPT | Provider model IDTEE/gemma4-31b | Regionglobal | Input / 1M$0.40 | Output / 1M$1 | Context262.1K | Updated |
Provider-specific output speed and catalog latency for Gemma 4 31B. Runtime does not affect the capability score.
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.
Technical details for the model's default version.
Available versions of this model. The score column identifies the version used in the overall ranking.
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionGemma 4 31B | Released | LLMBoard58.08 | Parameters30.7B | Context262.1K | Max output262.1K | Open weightsYes | LicenseApache 2.0 |
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Key information about Gemma 4 31B and its available data.
Gemma 4 31B is a large language model from Google based on the same research as Gemini 3. It uses Per-Layer Embeddings, Shared KV Cache, alternating sliding-window and global attention, and variable aspect ratio vision encoding.
Data as of 2026-10-22.
Common questions about Gemma 4 31B.
Gemma 4 31B's default version was released on Apr 2, 2026.
No official standard PAYG price is currently available for Gemma 4 31B. The lowest tracked third-party offer starts at $0.10 input and $0.30 output via FastRouter.
Gemma 4 31B was created by Google.
The default version has a 262.1K token context window.
Yes. The default version is marked as open weight under Apache 2.0.
36 provider offerings are linked to the default version.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.