← All models

Gemini 3.1 Pro Preview

Google · released 2026-02-19 · 2 offers

Output 124 tokens/sFirst token 25 sContext 1M tokens

Top 1 cheapest providers (Adjusted $/task)

Within the active global provider, residency and confidentiality filters.

#ProviderAdjusted $/task
1Google

Composite

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

63.4

includes −7.5 for its Benchmaxxing signal (from 70.8; why, switch off in Options)

Benchmaxxing signal +7.5, medium Benchmaxxing tag · medium report →

AA CodingCoding Agent v1.4AA IntelligenceAA AgenticEpoch ECISoftware ECIDesignArenaAA Coding: percentile 78AA Intelligence: percentile 87AA Agentic: percentile 42DesignArena: percentile 26

AA Coding 68.8Coding Agent v1.4 AA Intelligence 30.4AA Agentic 10.3Epoch ECI Software ECI DesignArena 1141/1078

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

Benchmark sheet

37 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):
  • DesignArena Web Apps (agentic) · attached
  • DesignArena Full-Stack · attached
Compare this model →

Agentic

  • AA-AnalystAgent6341.3%

    AA-AnalystAgent published 2026-09-10 · Published board — Tests analyst tasks using agentic Python execution across fourteen domains.

  • APEX-Agents-AA7232.0%

    APEX-Agents-AA published 2026-09-10 · Published board — Tests professional-service tasks that require agents to produce locally graded deliverables.

  • AA-Briefcase20459 Elo

    AA-Briefcase published 2026-09-10 · Published board — Tests multi-week professional knowledge-work projects with linked tasks and large source collections.

  • GDPval-AA v243904 Elo

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

  • Harvey LAB-AA1058.9%

    Harvey LAB-AA published 2026-09-10 · Published board — Tests legal-work deliverables across practice areas on Harvey's private task set. Artificial Analysis' run, graded by one LLM judge against task rubrics — not the same run or scale as Vals AI's HLAB row.

  • ITBench-AA3830.3%

    ITBench-AA published 2026-09-10 · Published board — Tests root-cause diagnosis from offline Kubernetes incident snapshots.

  • Terminal-Bench Hard (AA)9753.8%

    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)7273.8%

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

  • Terminal-Bench v4.0 (AA)614.0%

    Terminal-Bench v4.0 (AA) v4.0 · Published board — Tests terminal-based work on the 66-task release using mini-SWE-agent v2.4.6.

  • τ²-Bench Airline (OpenRouter run)7575.3%

    τ²-Bench Airline (OpenRouter run) published 2026-09-15 · Published board — Multi-turn service agents making tool calls under strict policy constraints. (OpenRouter's own reproducible run, as published on openrouter.ai/benchmarks.)

  • EBR-bench (Earthborne Rangers, Epoch AI)3114.3%

    EBR-bench (Earthborne Rangers, Epoch AI) published 2026-09-18 · Published board — Learning-capability test: models repeatedly play the obscure campaign board game Earthborne Rangers with note-taking, and the score measures whether results improve across playthroughs.

  • AA Agentic Index4210.3

    AA Agentic Index published 2026-09-18 · Published board — Artificial Analysis publishes one Agentic Index per model, measured on its primary configuration and relayed by OpenRouter's Benchmarks API; the value is attached at family scope on the deterministic representative. Artificial Analysis publishes this board without a version number; we keep the date each result was retained.

Coding

  • SciCode (AA subproblems) v1.0.19458.7%

    SciCode (AA subproblems) v1.0.1 · Published board — Tests scientific Python programming with scientist-annotated background information.

  • AA Coding Index7868.8

    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.

  • DesignArena Web Apps (agentic)271,141 Elo

    DesignArena Web Apps (agentic) published 2026-09-19 · Published board — Published Elo. Exact source attachment is retained; fewer than 200 battles excludes a row from radar normalization and anomaly peers.

  • DesignArena Full-Stack261,078 Elo

    DesignArena Full-Stack published 2026-09-19 · Published board — Published Elo. Exact source attachment is retained; fewer than 200 battles excludes a row from radar normalization and anomaly peers.

Efficiency

Instruction-following

Knowledge

Long-context

  • GDP.pdf (AA)7217.8%

    GDP.pdf (AA) published 2026-09-10 · Published board — Tests professional reasoning over long PDFs with AA document preparation and grading.

  • AA-LCR v1.19582.0%

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

  • MLCR-AA5715.6%

    MLCR-AA published 2026-09-10 · Published board — Tests medical-record synthesis and reasoning across long, fragmented case documents.

Math

  • ArXivMath 06/2026 (MathArena) v2026-062066.7%

    ArXivMath 06/2026 (MathArena) v2026-06 · Published board — Research-level math problems with a checkable final answer, drawn from arXiv papers submitted in June 2026, so they postdate most training data.

  • BrokenArXiv 06/2026 (MathArena) v2026-062017.6%

    BrokenArXiv 06/2026 (MathArena) v2026-06 · Published board — Plausible but false proof statements taken from June 2026 arXiv papers; a model scores by refusing to prove them and saying the statement is false as written.

  • FrontierMath Tiers 1–3 v2 (Epoch AI)3659.6%

    FrontierMath Tiers 1–3 v2 (Epoch AI) v2 · Published board — Unpublished, expert-written mathematics problems from undergraduate to research level with automatically checkable answers, run by Epoch AI on its private v2 set.

  • FrontierMath Tier 4 v2 (Epoch AI)2726.8%

    FrontierMath Tier 4 v2 (Epoch AI) v2 · Published board — The hardest, research-level tier of Epoch AI's unpublished FrontierMath problems, run by Epoch AI on its private v2 set.

Reasoning

  • SimpleBench10079.6%

    SimpleBench published 2026-09-10 · Published board — A multiple-choice text benchmark of over 200 questions covering spatio-temporal reasoning, social intelligence, and linguistic adversarial robustness, on which a non-specialized human baseline outperforms every tested LLM.

  • Chess Puzzles (Epoch AI)9655.0%

    Chess Puzzles (Epoch AI) published 2026-09-18 · Published board — Best-move selection on 100 novel chess positions generated programmatically by Epoch AI, each with a single Stockfish-verified best move; probes spatial reasoning and planning.

  • AA Intelligence Index8730.4

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

Science

Tool-use

  • AutomationBench-AA v1.0.65935.4%

    AutomationBench-AA v1.0.6 · Published board — Tests multi-app SaaS workflows through REST tools on a held-out AutomationBench split.

  • EnterpriseOps-Gym-AA5542.2%

    EnterpriseOps-Gym-AA published 2026-09-10 · Published board — Tests enterprise workflows through MCP tools against resettable application environments.

  • τ²-Bench Telecom (AA)9595.6%

    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) v1.0.15621.4%

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

Vision

Writing

Unusual results

3 threshold-crossing signals flagged · 35 eligible benchmark families

How flags are calculated

Heuristic screen, not statistical significance: benchmark families are correlated and source uncertainty is unknown. Peer evidence needs ≥ 20 independently measured matched configurations from ≥ 10 distinct model families. A flag needs a directed population z-score of magnitude ≥ 1.5 and a gap of ≥ 1.5 from the leave-one-benchmark-family-out mean z in the same direction, over ≥ 5 other benchmark families.

  • unusually strong Humanity's Last Exam (AA text-only) published 2026-09-10
    Why
    Observed: 0.47034 fraction
    Peer mean 0.15283 · peer sd 0.14006 · n 608 · families 449
    Directed z 2.267 · baseline z 0.474 · gap 1.793 · profile n 34
    0.47034 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
    Evidence
    Axis: Humanity's Last Exam (AA text-only) · published 2026-09-10 · Published board
    Exact value: 0.470342910101946 fraction
    Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
    Observation id: aa:bbd93ebe-80da-4594-bb19-61e69d0331df:hle
  • unusually strong Terminal-Bench Hard (AA)
    Why
    Observed: 0.53788 fraction
    Peer mean 0.18472 · peer sd 0.16951 · n 432 · families 315
    Directed z 2.083 · baseline z 0.479 · gap 1.604 · profile n 34
    0.53788 fractionmeasuredobserved 2026-09-10artificialanalysis.ai
    Evidence
    Axis: Terminal-Bench Hard (AA) · pinned revision 74221fb · Published board
    Exact value: 0.537878787878788 fraction
    Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
    Observation id: aa:bbd93ebe-80da-4594-bb19-61e69d0331df:terminalbenchHard
  • unusually strong AA-Omniscience Index published 2026-09-10
    Why
    Observed: 31.88333 points
    Peer mean -30.70814 · peer sd 31.08454 · n 520 · families 366
    Directed z 2.014 · baseline z 0.482 · gap 1.532 · profile n 34
    31.88333 pointsmeasuredobserved 2026-09-10artificialanalysis.ai
    Evidence
    Axis: AA-Omniscience Index · published 2026-09-10 · Published board
    Exact value: 31.8833333333333 points
    Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
    Observation id: aa:bbd93ebe-80da-4594-bb19-61e69d0331df:omniscience
Missing coverage · 104 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.

Token offers by platform · 1 offers (Adjusted $/task)

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

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

OpenRouter (1)

Google
Gemini 3.1 Pro Preview — benchmarks & cost | Benchmark Heaven