← All models

Gemma 4 31B (Non-reasoning)

open weights
Google · released 2026-04-02 · 19 offers

Output 41 tokens/sFirst token 0.9 sContext 256K tokens

Top 5 cheapest providers (Adjusted $/task)

The same list price can give a different adjusted $/task (caching, token efficiency) — click a price for its inputs.

Within the active global provider, residency and confidentiality filters.

#ProviderAdjusted $/task
1Chutes
2Chutes
3DeepInfra
4Parasail
5Venice

Composite

4 of 7 inputs · 2 from the model family6 radar axes: DesignArena's two boards share one

30.3

includes −5.3 for its Benchmaxxing signal (from 35.6; why, switch off in Options)

Benchmaxxing signal +5.3, light Benchmaxxing tag, uncertain: The 80 % interval reaches below zero — treat this tag as uncertain · light report →The 80 % interval reaches below zero — treat this tag as uncertain.

AA CodingCoding Agent v1.4AA IntelligenceAA AgenticEpoch ECISoftware ECIDesignArenaAA Coding: percentile 39AA Intelligence: percentile 58Epoch ECI: percentile 29Software ECI: percentile 19

AA Coding 33.2Coding Agent v1.4 AA Intelligence 13.9AA Agentic Epoch ECI 142.7Software ECI 144.1DesignArena —/—

Radar: percentile among all models measured on each input; a gap means not measured.

Benchmark sheet

14 of 140 registered benchmark versions · bars show the percentile among all models measured on each benchmark.

Composite attachments (used in the score, not counted as exact benchmarks):
  • Epoch ECI · attached
  • Software ECI · attached
Compare this model →

Agentic

  • GDPval-AA v233691 Elo

    GDPval-AA v2 v2 · Published board — Tests professional knowledge-work deliverables across occupations using AA's Stirrup harness.

  • Terminal-Bench Hard (AA)7230.3%

    Terminal-Bench Hard (AA) pinned revision 74221fb · Published board — Tests a pinned 44-task hard subset of terminal-based work using Terminus 2.

  • Terminal-Bench v2.1 (AA)3329.2%

    Terminal-Bench v2.1 (AA) v2.1 · Published board — Tests terminal-based work on the 89-task verified refresh using Terminus 2.

Coding

  • AA Coding Index3933.2

    AA Coding Index published 2026-09-19 · Published board — Artificial Analysis publishes this board without a version number; we keep the date each result was retained.

Instruction-following

Knowledge

Long-context

  • AA-LCR v1.14546.7%

    AA-LCR v1.1 v1.1 · Published board — Tests reasoning across multiple long documents with corrected answer keys and grading.

Reasoning

Safety/Alignment

Science

Tool-use

  • τ²-Bench Telecom (AA)5965.5%

    τ²-Bench Telecom (AA) published 2026-09-10 · Published board — Tests dual-control telecom agents that coordinate tool use with a simulated user.

  • τ³-Banking (AA) v1.0.1258.9%

    τ³-Banking (AA) v1.0.1 · Published board — Tests banking support agents that retrieve policies and change account state through tools.

Vision

Missing coverage · 129 benchmark versions

No result does not mean a zero, or that the model was never tested. Collection failures and disputed versions retain their distinct status.

Variants / reasoning settings

Artificial Analysis snapshot 2026-09-19 · Data: Artificial Analysis · Data: Epoch AI (CC BY)

VariantAA CodingAA Intelligence
Gemma 4 31B (Reasoning)43.415.4
Gemma 4 31B (Non-reasoning)33.213.9
Token offers by platform · 17 offers (Adjusted $/task)

Click any underlined price to see how it is estimated and where each input comes from. How we calculate adjusted cost.

17 offers within the active global filters; “—” means the catalog is active but no public token price is available.

Chutes (1)

Chutes

OpenRouter (13)

Chutes
DeepInfra
Parasail
Venice
CoreWeave
DeepInfra
Novita
Together
ModelRun
Crusoe
DeepInfra
SambaNova
SiliconFlow

TrustedTokens (1)

TrustedTokens

AWS Bedrock (1)

AWS Bedrock

STACKIT (1)

STACKIT
Gemma 4 31B (Non-reasoning) — benchmarks & cost | Benchmark Heaven