← All models

Gemini 3.6 Flash (high)

deprecated by benchmark source
Google · released 2026-07-21 · 4 offers

Output 212 tokens/sFirst token 12 sContext 1M tokens

Top 2 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
1Google
2Google Vertex AI

Composite

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

70.1

includes −6.1 for its Benchmaxxing signal (from 76.2; why, switch off in Options)

Benchmaxxing signal +6.1, medium Benchmaxxing tag, uncertain: The 80 % interval reaches below zero — treat this tag as uncertain · medium report →The 80 % interval reaches below zero — treat this tag as uncertain.

AA CodingCoding Agent v1.4AA IntelligenceAA AgenticEpoch ECISoftware ECIDesignArenaAA Coding: percentile 80Coding Agent v1.4: percentile 28AA Intelligence: percentile 91AA Agentic: percentile 72Epoch ECI: percentile 63Software ECI: percentile 52DesignArena: percentile 43

AA Coding 69.2Coding Agent v1.4 47.2AA Intelligence 34.3AA Agentic 30.2Epoch ECI 154.3Software ECI 152.7DesignArena 1211/1188

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

Benchmark sheet

42 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
  • DesignArena Web Apps (agentic) · attached
  • DesignArena Full-Stack · attached
Compare this model →

Agentic

  • AA-Briefcase50953 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 v2741,331 Elo

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

  • Harvey LAB-AA5285.1%

    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.

  • Terminal-Bench v2.1 (AA)7677.5%

    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)667.1%

    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.

  • ApprenticeBench API (NeoCognition)012.0%

    ApprenticeBench API (NeoCognition) published 2026-09-14 · Claude Code — An agent completes the same 100 sequential accounts-payable tasks in the Odoo ERP with diminishing mentoring, using dedicated application API calls instead of the screen interface.

  • Vals Index v2 (Vals AI)4355.4%

    Vals Index v2 (Vals AI) v2 · Published board — GDP-weighted average of agentic model performance across finance, coding and legal tasks.

  • Finance Agent v2 (Vals Index v2)6756.3%

    Finance Agent v2 (Vals Index v2) v2 · Published board — Multi-step financial reasoning tasks.

  • Terminal-Bench 2.1 (Vals Index v2)5773.8%

    Terminal-Bench 2.1 (Vals Index v2) v2 · Published board — Command-line interface problem solving, as run by Vals AI.

  • HLAB — Harvey's Legal Agent Benchmark (Vals Index v2)283.3%

    HLAB — Harvey's Legal Agent Benchmark (Vals Index v2) v2 · Published board — Long-horizon legal work product creation. Vals AI's run of Harvey's Legal Agent Benchmark, reported as accuracy — not comparable with Artificial Analysis' Harvey LAB-AA row.

  • τ²-Bench Airline (OpenRouter run)6173.0%

    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.)

  • AA Agentic Index7230.2

    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

Efficiency

Knowledge

Long-context

  • GDP.pdf (AA)7017.4%

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

  • AA-LCR v1.18980.0%

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

  • MLCR-AA4914.4%

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

Math

  • FrontierMath Tiers 1–3 v2 (Epoch AI)3058.9%

    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)1122.0%

    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

  • Chess Puzzles (Epoch AI)7640.0%

    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.

  • Mystery Game Puzzles (Epoch AI)4930.0%

    Mystery Game Puzzles (Epoch AI) published 2026-09-18 · Published board — Best-move selection on 100 mid-game positions of a well-known game whose identity Epoch deliberately keeps undisclosed, generated programmatically like Chess Puzzles.

  • AA Intelligence Index9134.3

    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 v1.0.67653.0%

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

  • τ³-Banking (AA) v1.0.16829.9%

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

  • Excel Modeling Benchmark (Vals Index v2)5965.4%

    Excel Modeling Benchmark (Vals Index v2) v2 · Published board — Building and editing financial models in spreadsheets.

Vision

Missing coverage · 99 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.

SUBSCRIPTION PLAN

GitHub Copilot

Current usage-based billing · model token cost is converted to AI Credits at 1 credit = $0.01.

Input $0.750 / 1M
Cached input $0.075 / 1M
Output $3.75 / 1M
Status GA

Official promotional token rates through December 31, 2026; no post-promotion rate inferred.

Token offers by platform · 3 offers (Adjusted $/task)

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

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

OpenRouter (2)

Google
Google

Google Vertex AI (1)

Google Vertex AI
Gemini 3.6 Flash (high) — benchmarks & cost | Benchmark Heaven