← All models

GPT-6 Luna (xhigh)

★ featured
OpenAI · released 2026-09-22 · 6 offers

Output 141 tokens/sFirst token 9.5 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
1Azure
2Amazon Bedrock

Composite

1 of 7 inputs6 radar axes: DesignArena's two boards share one

69.0

 Thin data · 1/7Based on only 1 of 7 Composite inputs — treat this rank as uncertain

dominance-adjusted from 77.9: a better-measured model that is at least as good on each of these inputs ranks above it

AA CodingCoding Agent v1.4AA IntelligenceAA AgenticEpoch ECISoftware ECIDesignArenaAA Intelligence: percentile 89

AA Coding Coding Agent v1.4 AA Intelligence 33.9AA Agentic Epoch ECI Software ECI DesignArena —/—

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

Benchmark sheet

13 of 292 registered benchmark versions · bars show the percentile among all models measured on each benchmark.

Compare this model →

Agentic

  • AA-Briefcase v1.1331,217 Elo

    AA-Briefcase v1.1 v1.1 · Published board — Tests multi-week professional knowledge-work projects with linked tasks and large source collections.

  • GDPval-AA v2.1331,297 Elo

    GDPval-AA v2.1 v2.1 · Published board — Tests professional knowledge-work deliverables across occupations using AA's Stirrup harness.

  • Terminal-Bench v4.0 (AA, upstream timeouts)198.1%

    Terminal-Bench v4.0 (AA, upstream timeouts) 4.0-upstream-timeouts · Published board — Tests terminal-based work on the 66-task release using AA's mini-swe-agent harness with the tasks' own timeouts.

Coding

  • SciCode (AA subproblems) v1.0.16551.7%

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

Efficiency

Knowledge

Long-context

  • GDP.pdf (AA)2416.8%

    GDP.pdf (AA) published 2026-09-21 · Published board — Tests professional reasoning over long PDFs with AA document preparation and grading.

  • AA-LCR v1.18880.0%

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

Reasoning

Science

Tool-use

  • AutomationBench-AA v1.0.66647.8%

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

Vision

Missing coverage · 283 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 2026-09-23 · Data: Artificial Analysis · Data: Epoch AI (CC BY)

VariantAA CodingAA Intelligence
GPT-6 Luna (max)37.3
GPT-6 Luna (xhigh)33.9
GPT-6 Luna (high)32.1
GPT-6 Luna (medium)29.5
GPT-6 Luna (low)20.9
GPT-6 Luna (Non-reasoning)18.3

SUBSCRIPTION PLAN

GitHub Copilot

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

Input $0.100 / 1M
Cached input $0.010 / 1M
Cache write $0.125 / 1M
Output $0.500 / 1M
Status GA
Token offers by platform · 4 offers (Adjusted $/task)

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

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

OpenRouter (4)

Azure
Azure
Amazon Bedrock
Azure
GPT-6 Luna (xhigh) — benchmarks & cost | Benchmark Heaven