llmboard.aiAI model intelligence
Home

Model Rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision
Image GenerationImage Editing
Video GenerationImage to VideoVideo Editing
Text to SpeechSpeech to Text
Embeddings

Efficiency

Chat Token PricingImage PricingVideo PricingAudio Pricing
Chat Speed & LatencyProvider Reliability

Benchmarks

GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-Pro
All Benchmarks

Tools

Model Directory

Scoring & Data

Scoring & Data
1367 models808 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll Benchmarks
llmboard.aiCopyright 2026 llmboard.ai

Google model product

Gemma 4 31B

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

LLMBoard Score58.1Gemma 4 31B
Coverage60%12 benchmark families
Context window262.1KTokens
Official input priceN/AOfficial price unavailable

On this page

  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Runtime
  • Specification
  • Versions
  • Similar models
  • About
  • FAQ

Gemma 4 31B Capability Profile

This profile uses the model's current scored version. Arena ratings and prices are shown separately.

Gemma 4 31B LLMBoard score breakdown

Gemma 4 31B Benchmark Results

Benchmark scores for Gemma 4 31B.

27 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
BenchmarkBIG-Bench Extra HardScore74.40%Rank01Participants11Percentile100.00%EvidenceCEvaluatedOct 22, 2026
BenchmarkMedXpertQAScore61.30%Rank05Participants12Percentile63.64%EvidenceCEvaluatedOct 22, 2026
Benchmarkt2-benchScore86.40%Rank05Participants23Percentile81.82%EvidenceCEvaluatedOct 22, 2026
BenchmarkMRCR v2 (8-needle)Score66.40%Rank08Participants25Percentile70.83%EvidenceCEvaluatedOct 22, 2026
BenchmarkMathVisionScore85.60%Rank12Participants38Percentile70.27%EvidenceCEvaluatedOct 22, 2026
BenchmarkMMMLUScore88.40%Rank18Participants51Percentile66.00%EvidenceCEvaluatedOct 22, 2026
BenchmarkMMLU-ProScore85.20%Rank19Participants142Percentile87.23%EvidenceCEvaluatedOct 22, 2026
BenchmarkAIME 2026Score89.20%Rank20Participants27Percentile26.92%EvidenceCEvaluatedOct 22, 2026
BenchmarkAA IFBenchScore75.58%Rank21Participants168Percentile88.02%EvidenceBEvaluatedN/A
BenchmarkMMMU-ProScore76.90%Rank25Participants73Percentile66.67%EvidenceCEvaluatedOct 22, 2026
BenchmarkLiveCodeBench v6Score80.00%Rank29Participants67Percentile57.58%EvidenceCEvaluatedOct 22, 2026
BenchmarkLM Arena Document Style ControlScore1,444.51 ratingRank29Participants38Percentile24.32%EvidenceAEvaluatedSep 13, 2026
BenchmarkLM Arena DocumentScore1,424.51 ratingRank30Participants38Percentile21.62%EvidenceAEvaluatedSep 13, 2026
BenchmarkLM Arena VisionScore1,276.47 ratingRank30Participants113Percentile74.11%EvidenceAEvaluatedOct 19, 2026
BenchmarkLM Arena Vision Style ControlScore1,261.85 ratingRank35Participants113Percentile69.64%EvidenceAEvaluatedOct 19, 2026
BenchmarkAA SciCode SubtasksScore45.49%Rank45Participants89Percentile50.00%EvidenceBEvaluatedN/A
BenchmarkLM Arena TextScore1,442.73 ratingRank51Participants218Percentile76.96%EvidenceAEvaluatedOct 20, 2026
BenchmarkLM Arena Text FactualityScore1,449.21 ratingRank51Participants131Percentile61.54%EvidenceAEvaluatedOct 20, 2026
BenchmarkLM Arena Text Style ControlScore1,452.10 ratingRank55Participants218Percentile75.12%EvidenceAEvaluatedOct 20, 2026
BenchmarkHumanity's Last ExamScore26.50%Rank60Participants109Percentile45.37%EvidenceCEvaluatedOct 22, 2026
BenchmarkAA GPQA DiamondScore85.66%Rank64Participants199Percentile68.18%EvidenceBEvaluatedN/A
BenchmarkGPQAScore84.30%Rank74Participants256Percentile71.37%EvidenceCEvaluatedOct 22, 2026
BenchmarkAA HLE Text No ToolsScore23.63%Rank75Participants200Percentile62.81%EvidenceBEvaluatedN/A
BenchmarkLM Arena WebdevScore1,367.44 ratingRank79Participants107Percentile26.42%EvidenceAEvaluatedOct 19, 2026
BenchmarkAA CritPtScore1.43%Rank85Participants200Percentile57.79%EvidenceBEvaluatedN/A
BenchmarkAA LCR v1.1Score69.67%Rank91Participants193Percentile53.13%EvidenceBEvaluatedN/A
BenchmarkAA Omniscience AccuracyScore20.03%Rank126Participants201Percentile37.50%EvidenceBEvaluatedN/A

Gemma 4 31B Arena Results

Preference and agent-evaluation results for the default version.

30 of 88 rows
Columns

Show columns

Sort by
Arena
Category
Rank
Rating / score
Votes
Observations
Result date
ArenavisionCategorycaptioningRank16Rating / score1,217.52Votes106ObservationsN/AResult dateOct 19, 2026
ArenavisionCategorycreative writing visionRank20Rating / score1,284.73Votes2,703ObservationsN/AResult dateOct 19, 2026
ArenavisionCategoryentity recognitionRank24Rating / score1,225.71Votes359ObservationsN/AResult dateOct 19, 2026
ArenavisionCategoryhumorRank24Rating / score1,279.94Votes1,659ObservationsN/AResult dateOct 19, 2026
Arenavision style controlCategorycaptioningRank24Rating / score1,170.08Votes106ObservationsN/AResult dateOct 19, 2026
Arenavision style controlCategorycreative writing visionRank24Rating / score1,264.55Votes2,703ObservationsN/AResult dateOct 19, 2026
Arenavision style controlCategoryhomeworkRank24Rating / score1,303.82Votes6,435ObservationsN/AResult dateOct 19, 2026
ArenavisionCategoryhomeworkRank25Rating / score1,309.71Votes6,435ObservationsN/AResult dateOct 19, 2026
Arenavision style controlCategoryentity recognitionRank26Rating / score1,196.20Votes359ObservationsN/AResult dateOct 19, 2026
Arenavision style controlCategoryhumorRank28Rating / score1,259.58Votes1,659ObservationsN/AResult dateOct 19, 2026
Arenadocument style controlCategoryoverallRank29Rating / score1,444.51Votes12,326ObservationsN/AResult dateSep 13, 2026
ArenadocumentCategoryoverallRank30Rating / score1,424.51Votes12,326ObservationsN/AResult dateSep 13, 2026
ArenavisionCategorychineseRank30Rating / score1,325.85Votes2,734ObservationsN/AResult dateOct 19, 2026
ArenavisionCategoryoverallRank30Rating / score1,276.47Votes40,219ObservationsN/AResult dateOct 19, 2026
Arenavision style controlCategorychineseRank30Rating / score1,305.45Votes2,734ObservationsN/AResult dateOct 19, 2026
ArenatextCategoryrussianRank31Rating / score1,459.68Votes824ObservationsN/AResult dateOct 20, 2026
ArenavisionCategoryocrRank33Rating / score1,281.94Votes28,054ObservationsN/AResult dateOct 19, 2026
Arenatext style controlCategoryexpertRank34Rating / score1,497.92Votes501ObservationsN/AResult dateOct 20, 2026
Arenatext style controlCategoryrussianRank35Rating / score1,467.36Votes824ObservationsN/AResult dateOct 20, 2026
Arenavision style controlCategoryocrRank35Rating / score1,273.46Votes28,054ObservationsN/AResult dateOct 19, 2026
Arenavision style controlCategoryoverallRank35Rating / score1,261.85Votes40,219ObservationsN/AResult dateOct 19, 2026
ArenavisionCategoryenglishRank36Rating / score1,270.96Votes15,807ObservationsN/AResult dateOct 19, 2026
Arenavision style controlCategorydiagramRank37Rating / score1,282.89Votes10,238ObservationsN/AResult dateOct 19, 2026
ArenavisionCategorydiagramRank38Rating / score1,282.52Votes10,238ObservationsN/AResult dateOct 19, 2026
Arenavision style controlCategoryenglishRank38Rating / score1,256.16Votes15,807ObservationsN/AResult dateOct 19, 2026
ArenatextCategorymathRank44Rating / score1,462.65Votes428ObservationsN/AResult dateOct 20, 2026
Arenatext style controlCategoryinstruction followingRank44Rating / score1,453.57Votes1,798ObservationsN/AResult dateOct 20, 2026
Arenatext style controlCategorylonger queryRank44Rating / score1,470.07Votes1,797ObservationsN/AResult dateOct 20, 2026
ArenatextCategoryindustry writing and literature and languageRank45Rating / score1,431.68Votes1,421ObservationsN/AResult dateOct 20, 2026
ArenatextCategoryindustry mathematicalRank46Rating / score1,465.02Votes345ObservationsN/AResult dateOct 20, 2026

Gemma 4 31B Pricing

Official vendor API pricing appears first, followed by individual provider offers.

Official API
N/A
Official provider
N/A
Lowest third-party
From $0.10 input, $0.30 output per 1M via FastRouter
Tracked offerings
36
30 of 34 rows
Columns

Show columns

Sort by
Provider
Provider model ID
Region
Input / 1M
Output / 1M
Context
Updated
ProviderNvidiaProvider model IDgoogle/gemma-4-31b-itRegionglobalInput / 1MN/AOutput / 1MN/AContext256KUpdatedOct 23, 2026
ProviderRequestyProvider model IDgemma-4-31b-itRegionglobalInput / 1MN/AOutput / 1MN/AContext262.1KUpdatedOct 23, 2026
ProviderPoeProvider model IDgoogle/gemma-4-31bRegionglobalInput / 1MN/AOutput / 1MN/AContext262.1KUpdatedOct 23, 2026
ProviderAMDProvider model IDGemma-4-31B-ITRegionglobalInput / 1MN/AOutput / 1MN/AContext262.1KUpdatedOct 23, 2026
ProviderFastRouterProvider model IDgoogle/gemma-4-31b-itRegionglobalInput / 1M$0.10Output / 1M$0.30Context262.1KUpdatedOct 23, 2026
ProviderDevPass (LLM Gateway)Provider model IDgemma-4-31b-itRegionglobalInput / 1M$0.10Output / 1M$0.25Context262.1KUpdatedOct 23, 2026
ProviderKilo GatewayProvider model IDgoogle/gemma-4-31b-itRegionglobalInput / 1M$0.10Output / 1M$0.34Context262.1KUpdatedOct 23, 2026
ProviderCoreWeaveProvider model IDgoogle/gemma-4-31B-itRegionglobalInput / 1M$0.10Output / 1M$0.34Context262.1KUpdatedOct 23, 2026
ProviderKenariProvider model IDgemma-4-31b-itRegionglobalInput / 1M$0.1029Output / 1M$0.4057Context262.1KUpdatedOct 23, 2026
ProviderLilacProvider model IDgoogle/gemma-4-31b-itRegionglobalInput / 1M$0.11Output / 1M$0.35Context262.1KUpdatedOct 23, 2026
ProviderOrcaRouterProvider model IDgoogle/gemma-4-31b-itRegionglobalInput / 1M$0.13Output / 1M$0.38Context262.1KUpdatedOct 23, 2026
ProviderNanoGPTProvider model IDgoogle/gemma-4-31b-itRegionglobalInput / 1M$0.14Output / 1M$0.40Context262.1KUpdatedOct 23, 2026
ProviderHugging FaceProvider model IDgoogle/gemma-4-31B-itRegionglobalInput / 1M$0.14Output / 1M$0.40Context262.1KUpdatedOct 23, 2026
ProviderCrusoeProvider model IDgoogle/gemma-4-31b-itRegionglobalInput / 1M$0.14Output / 1M$0.40Context262.1KUpdatedOct 23, 2026
ProviderMerge GatewayProvider model IDgoogle/gemma-4-31b-itRegionglobalInput / 1M$0.14Output / 1M$0.40Context262.1KUpdatedOct 23, 2026
ProviderOllama CloudProvider model IDgemma4:31bRegionglobalInput / 1M$0.14Output / 1M$0.40Context262.1KUpdatedOct 23, 2026
ProviderFriendliProvider model IDgoogle/gemma-4-31B-itRegionglobalInput / 1M$0.14Output / 1M$0.40Context262.1KUpdatedOct 23, 2026
ProviderVercel AI GatewayProvider model IDgoogle/gemma-4-31b-itRegionglobalInput / 1M$0.14Output / 1M$0.40Context262.1KUpdatedOct 23, 2026
ProviderNovita AIProvider model IDgoogle/gemma-4-31b-itRegionglobalInput / 1M$0.14Output / 1M$0.40Context262.1KUpdatedOct 23, 2026
ProviderAbacusProvider model IDgoogle/gemma-4-31b-itRegionglobalInput / 1M$0.14Output / 1M$0.40Context262.1KUpdatedOct 23, 2026
ProviderNeuralwattProvider model IDgemma-4-31bRegionglobalInput / 1M$0.144Output / 1M$0.42Context262.1KUpdatedOct 23, 2026
ProviderDigitalOceanProvider model IDgemma-4-31B-itRegionglobalInput / 1M$0.18Output / 1M$0.50Context256KUpdatedOct 23, 2026
ProviderDeep InfraProvider model IDgoogle/gemma-4-31B-itRegionglobalInput / 1M$0.20Output / 1M$0.40Context262.1KUpdatedOct 23, 2026
ProviderOpenRouterProvider model IDgoogle/gemma-4-31b-itRegionglobalInput / 1M$0.20Output / 1M$0.40Context262.1KUpdatedOct 23, 2026
Providerai&Provider model IDgoogle/gemma-4-31b-itRegionglobalInput / 1M$0.20Output / 1M$0.50Context262.1KUpdatedOct 23, 2026
ProviderCortecsProvider model IDgemma-4-31b-itRegionglobalInput / 1M$0.223Output / 1M$0.39Context262KUpdatedOct 23, 2026
ProviderInfomaniakProvider model IDgoogle/gemma-4-31B-itRegionglobalInput / 1M$0.25Output / 1M$0.50Context100KUpdatedOct 23, 2026
ProviderBerget.AIProvider model IDgoogle/gemma-4-31B-itRegionglobalInput / 1M$0.2804Output / 1M$0.5608Context128KUpdatedOct 23, 2026
ProviderSambaNovaProvider model IDgemma-4-31B-itRegionglobalInput / 1M$0.38Output / 1M$1.15Context131.1KUpdatedOct 23, 2026
ProviderNanoGPTProvider model IDTEE/gemma4-31bRegionglobalInput / 1M$0.40Output / 1M$1Context262.1KUpdatedOct 23, 2026

Gemma 4 31B Runtime Performance

Provider-specific output speed and catalog latency for Gemma 4 31B. 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 31B Specifications

Technical details for the model's default version.

Version
Gemma 4 31B
Released
Apr 2, 2026
Knowledge cutoff
Jan 1, 2025
Parameters
30.7B
Context window
262.1K
Max output
262.1K
Inputs
audio, image, text, video
Outputs
text
Open weights
Yes
License
Apache 2.0

Gemma 4 31B Versions

Available versions of this model. The score column identifies the version used in the overall ranking.

1 row
Columns

Show columns

Sort by
Version
Released
LLMBoard
Parameters
Context
Max output
Open weights
License
VersionGemma 4 31BReleasedApr 2, 2026LLMBoard58.08Parameters30.7BContext262.1KMax output262.1KOpen weightsYesLicenseApache 2.0

Models similar to Gemma 4 31B

Recommendations prioritize the same model type and family, then the closest LLMBoard score.

#94+1.29
GO

Gemini 3.5 Flash Cyber

Google

59.37 LLMBoard

Details
#86+4.63
GO

Gemini 3.8 Flash Cyber

Google

62.71 LLMBoard

Details
#121-5.64
GO

Gemini 3.5 Flash Lite

Google

52.44 LLMBoard

Details
#81+5.97
GO

Gemini 3 Flash

Google

64.05 LLMBoard

Details
#131-7.48
GO

Gemma 4 26B A4B

Google

50.60 LLMBoard

Details
#134-7.76
GO

Gemini 3.1 Flash Lite

Google

50.32 LLMBoard

Details

What is Gemma 4 31B?

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.

FAQ

Common questions about Gemma 4 31B.

When was Gemma 4 31B released?

Gemma 4 31B's default version was released on Apr 2, 2026.

How much does Gemma 4 31B cost?

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.

Who created Gemma 4 31B?

Gemma 4 31B was created by Google.

What is the context window for Gemma 4 31B?

The default version has a 262.1K token context window.

Is Gemma 4 31B open weight?

Yes. The default version is marked as open weight under Apache 2.0.

How many API providers offer Gemma 4 31B?

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.

Browse runtime rankings