GPT-6 Astra (Xhigh)
Output 55 tokens/sFirst token 89 sContext 1M tokens
Top 4 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.
| # | Provider | Price channel | Raw input $/1M | Raw output $/1M | Adjusted $/task |
|---|---|---|---|---|---|
| 1 | Azurevia OpenRouter — Price via OpenRouter: OpenRouter's price for Azure's endpoint (https://openrouter.ai/openai/gpt-6-astra/providers), collected 2026-11-03. | via OpenRouter — Price via OpenRouter: OpenRouter's price for Azure's endpoint (https://openrouter.ai/openai/gpt-6-astra/providers), collected 2026-11-03. | $10.00 | $50.00 | |
| 2 | Amazon Bedrockvia OpenRouter — Price via OpenRouter: OpenRouter's price for Amazon Bedrock's endpoint (https://openrouter.ai/openai/gpt-6-astra/providers), collected 2026-11-03. | via OpenRouter — Price via OpenRouter: OpenRouter's price for Amazon Bedrock's endpoint (https://openrouter.ai/openai/gpt-6-astra/providers), collected 2026-11-03. | $11.00 | $55.00 | |
| 3 | Azure AI Foundrydirect — Direct price: Azure AI Foundry's own price list (https://prices.azure.com/api/retail/prices), collected 2026-11-03. | direct — Direct price: Azure AI Foundry's own price list (https://prices.azure.com/api/retail/prices), collected 2026-11-03. | $10.00 | $50.00 | |
| 4 | T-Systems LLM Hubdirect — Direct price: T-Systems LLM Hub's own price list (https://docs.llmhub.t-systems.net/models/llms/), collected 2026-11-03. | direct — Direct price: T-Systems LLM Hub's own price list (https://docs.llmhub.t-systems.net/models/llms/), collected 2026-11-03. | $10.86 | $54.29 |
Composite
6 of 7 inputs · 4 from the model family6 radar axes: DesignArena's two boards share one92.8
AA Coding v4.x 75.9Coding Agent v1.4 —AA Intelligence 55.3AA Agentic —Epoch ECI 169.1Software ECI 167.9DesignArena 1313/1357
Radar: percentile among all models measured on each input; a gap means not measured.
Benchmark sheet
48 of 319 registered benchmark versions · bars show the percentile among all models measured on each benchmark.
13 of 52 values are OpenAI's own claims (†), not independent measurements; a matching independent result replaces a claim as soon as one exists.
- Epoch ECI · attached
- Software ECI · attached
- DesignArena Web Apps (agentic) · attached
- DesignArena Full-Stack · attached
Agentic
AA-Briefcase v1.1no percentile1,544 Elo
AA-Briefcase v1.1 v1.1 → · Published board — Tests multi-week professional knowledge-work projects with linked tasks and large source collections.
AA-Briefcase931,534 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 v2901,555 Elo
GDPval-AA v2 v2 → · Published board — Tests professional knowledge-work deliverables across occupations using AA's Stirrup harness.
GDPval-AA v2.1no percentile1,516 Elo
GDPval-AA v2.1 v2.1 → · Published board — Tests professional knowledge-work deliverables across occupations using AA's Stirrup harness.
Terminal-Bench v2.1 (AA)9789.1%
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)10059.6%
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.
Terminal-Bench v4.0 (AA, upstream timeouts)9559.6%
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.
ApprenticeBench CUA (NeoCognition)9161.0%
ApprenticeBench CUA (NeoCognition) published 2026-09-14 → · Codex — A computer-use agent operates the Odoo ERP through its screens across 100 sequential accounts-payable tasks with diminishing mentoring.
Terminal-Bench v4.0developer's claim57.9%† self-reported by the developer
Terminal-Bench v4.0 → · Codex — A benchmark to measure and evolve with the frontier of agent work, whose homepage leaderboard reports resolution rate on Terminal-Bench 4.0 tasks.
AutomationBench 1.0.6developer's claim39.0%† self-reported by the developer
AutomationBench 1.0.6 v1.0.6 → · Vendor-reported by OpenAI — AutomationBench 1.0.6 score OpenAI reports for its own GPT-6 models in the 2026-09-22 GPT-6 Sol and Luna launch post.
Agents' Last Exam V1developer's claim58.3%† self-reported by the developer
Agents' Last Exam V1 v1 → · Vendor-reported by OpenAI — Agents' Last Exam V1 score OpenAI reports for its own GPT-6 models in the 2026-09-22 GPT-6 Sol and Luna launch post.
OSWorld 2.0 offline (v2026.08.08 release)developer's claim71.3%† self-reported by the developer
OSWorld 2.0 offline (v2026.08.08 release) v2026.08.08 → · Vendor-reported by OpenAI — OSWorld 2.0 offline partial reward OpenAI reports for its own GPT-6 models in the 2026-09-22 GPT-6 Sol and Luna launch post.
Coding
SciCode (AA subproblems) v1.0.18155.7%
SciCode (AA subproblems) v1.0.1 → · Published board — Tests scientific Python programming with scientist-annotated background information.
DeepSWE (Datacurve, via Epoch AI)10074.1%
DeepSWE (Datacurve, via Epoch AI) published 2026-09-15 → · mini-SWE-agent — Pass rate of coding agents on original, long-horizon software engineering tasks, run by Datacurve with the mini-swe-agent harness.
FrontierCode 1.1 Main (Cognition)developer's claim50.6%† self-reported by the developer
FrontierCode 1.1 Main (Cognition) v1.1 → · Codex — Whether a maintainer would merge the agent's pull request, on tasks crafted by open-source maintainers and graded with tests, rubrics and verifiers.
SWE Atlas Codebase QnA (Scale AI)7859.1%
SWE Atlas Codebase QnA (Scale AI) published 2026-09-15 → · Published board — How well a coding agent answers deep questions about a real codebase, graded against expert rubrics.
SWE Atlas Refactoring (Scale AI)10059.0%
SWE Atlas Refactoring (Scale AI) published 2026-09-15 → · Published board — Whether a coding agent restructures production code while preserving its behaviour, graded by tests and rubrics.
SWE Atlas Test Writing (Scale AI)6750.7%
SWE Atlas Test Writing (Scale AI) published 2026-09-15 → · Published board — Whether a coding agent writes production-grade tests for real repositories, graded with rubrics and LLM judges.
VulcanBench Frontier v49589.2%
VulcanBench Frontier v4 v4 → · Codex — 23 behavioural-reconstruction tasks: the model must repair a replacement implementation of a legacy program until hidden tests confirm it reproduces the program’s real drift from its written spec; the combined score weights functional correctness 50%, lint/complexity 8.5%, security 8.5% and judged Code quality 33%.
WeirdML v310042.2%
WeirdML v3 v3 → · Published board — Agentic benchmark with 11 hand-made machine-learning tasks: a model must explore unfamiliar data, build and run analysis pipelines and produce results despite limited data, unspecified goals or very limited feedback.
DeepSWE v1.1developer's claim74.1%† self-reported by the developer
DeepSWE v1.1 v1.1 → · Vendor-reported by OpenAI — DeepSWE v1.1 score OpenAI reports for its own GPT-6 models in the 2026-09-22 GPT-6 Sol and Luna launch post.
FrontierCode 1.1 Extended (Cognition)developer's claim62.1%† self-reported by the developer
FrontierCode 1.1 Extended (Cognition) v1.1 → · Codex — Whether a maintainer would merge the agent's pull request, on the full 150-task FrontierCode set crafted by open-source maintainers and graded with tests, rubrics and verifiers.
AA Coding Index v4.x · frozen 2026-10-279175.9
AA Coding Index v4.x · frozen 2026-10-27 → · Published board — Artificial Analysis withdrew the Coding Index with Intelligence Index v5.0 (2026-10-28). These are the last v4.x values, frozen with their own date (2026-10-27).
DesignArena Web Apps (agentic)961,313 Elo
DesignArena Web Apps (agentic) published 2026-11-03 → · Published board — Published Elo. Exact source attachment is retained; fewer than 200 battles excludes a row from radar normalization and anomaly peers.
DesignArena Full-Stack1001,357 Elo
DesignArena Full-Stack published 2026-11-03 → · Published board — Published Elo. Exact source attachment is retained; fewer than 200 battles excludes a row from radar normalization and anomaly peers.
Efficiency
ApprenticeBench CUA cost per task (NeoCognition)9$14.37
ApprenticeBench CUA cost per task (NeoCognition) published 2026-09-14 → · Codex — ApprenticeBench's published USD cost per task for each CUA model-harness-effort configuration on the 100-task accounts-payable job.
FrontierCode 1.1 Main cost per rollout (Cognition)developer's claim$3.28† self-reported by the developer
FrontierCode 1.1 Main cost per rollout (Cognition) v1.1 → · Codex — Cognition's published mean USD spend per rollout for each FrontierCode 1.1 Main model and reasoning effort.
AutomationBench 1.0.6 cost per taskdeveloper's claim$1.50† self-reported by the developer
AutomationBench 1.0.6 cost per task v1.0.6 → · Published board — USD cost per AutomationBench 1.0.6 task OpenAI reports for its own GPT-6 models in the 2026-09-22 GPT-6 Sol and Luna launch post.
Cost to run AA Intelligence Index (total) v4.3.214$3,803
Cost to run AA Intelligence Index (total) v4.3.2 → · Published board — Cost to run AA Intelligence Index (total) results published by Artificial Analysis.
Cost per AA Intelligence Index task v4.3.2142.31
Cost per AA Intelligence Index task v4.3.2 → · Published board — Cost per AA Intelligence Index task results published by Artificial Analysis.
FrontierCode 1.1 Extended cost per rollout (Cognition)developer's claim$2.86† self-reported by the developer
FrontierCode 1.1 Extended cost per rollout (Cognition) v1.1 → · Codex — Cognition's published mean USD spend per rollout for each FrontierCode 1.1 Extended model and reasoning effort.
Agents' Last Exam V1 cost per taskdeveloper's claim$5.40† self-reported by the developer
Agents' Last Exam V1 cost per task v1 → · Published board — USD cost per Agents' Last Exam V1 task OpenAI reports for its own GPT-6 models in the 2026-09-22 GPT-6 Sol and Luna launch post.
DeepSWE v1.1 cost per taskdeveloper's claim$4.43† self-reported by the developer
DeepSWE v1.1 cost per task v1.1 → · Published board — USD cost per DeepSWE v1.1 task OpenAI reports for its own GPT-6 models in the 2026-09-22 GPT-6 Sol and Luna launch post.
OSWorld 2.0 offline (v2026.08.08 release) cost per taskdeveloper's claim$7.17† self-reported by the developer
OSWorld 2.0 offline (v2026.08.08 release) cost per task v2026.08.08 → · Published board — USD cost per OSWorld 2.0 offline (v2026.08.08 release) task OpenAI reports for its own GPT-6 models in the 2026-09-22 GPT-6 Sol and Luna launch post.
Knowledge
Humanity's Last Exam (AA text-only)9854.6%
Humanity's Last Exam (AA text-only) published 2026-09-10 → · Published board — Tests expert-level knowledge on AA's text-only Humanity's Last Exam subset.
AA-Omniscience Index9943.4
AA-Omniscience Index published 2026-09-10 → · Published board — Tests factual reliability while rewarding correct answers and penalizing hallucinations.
UGI NatInt9881.0
UGI NatInt published 2026-09-10 → · Published board — A private-question evaluation of general knowledge and reasoning across textbook, popular-culture and world-model topics.
Long-context
GDP.pdf (AA)10032.2%
GDP.pdf (AA) published 2026-09-10 → · Published board — Tests professional reasoning over long PDFs with AA document preparation and grading.
GDP.pdf (AA)no percentile32.2%
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.
Math
FrontierMath Tier 4 v2 (Epoch AI)9797.6%
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
ARC-AGI-19498.5%
ARC-AGI-1 v1 → · Published board — The first-generation ARC-AGI benchmark measuring passive fluid intelligence, with leaderboard score plotted against cost-per-task.
ARC-AGI-29493.3%
ARC-AGI-2 v2 → · Published board — The second-generation ARC-AGI benchmark of passive fluid intelligence, with leaderboard score plotted against cost-per-task.
AA Intelligence Index v5.0 · snapshot-2026-11-039555.3
AA Intelligence Index v5.0 · snapshot-2026-11-03 → · Published board — Artificial Analysis Intelligence Index v5.0. Models AA has not rescored on v5.0 are listed as estimates from their frozen v4.x value (isotonic fit over the models measured on both versions), never as measurements.
Science
CritPt (AA)9931.4%
CritPt (AA) published 2026-09-10 → · Published board — Tests research-level physics reasoning with Python, symbolic and numerical answers.
GPQA Diamond (AA)10096.3%
GPQA Diamond (AA) published 2026-09-10 → · Published board — Tests graduate-level biology, physics and chemistry knowledge on the Diamond subset.
Tool-use
AutomationBench-AA v1.0.69867.2%
AutomationBench-AA v1.0.6 → · Published board — Tests multi-app SaaS workflows through REST tools on a held-out AutomationBench split.
τ³-Banking (AA) v1.0.19043.1%
τ³-Banking (AA) v1.0.1 → · Published board — Tests banking support agents that retrieve policies and change account state through tools.
Uncensored
UGI Willingness573.20
UGI Willingness published 2026-09-10 → · Published board — A private-question evaluation of how far a model follows challenging instructions before refusing or deviating.
UGI9153.5
UGI published 2026-09-10 → · Published board — A private-question suite combining sensitive-topic knowledge with willingness to follow controversial instructions.
Vision
MMMU Pro (AA)9986.2%
MMMU Pro (AA) published 2026-09-10 → · Published board — Tests multimodal understanding using challenging ten-option questions.
Writing
UGI Writing9868.0
UGI Writing published 2026-09-10 → · Published board — A maintainer-owned writing evaluation considering intelligence, style, repetition and length adherence, informed by human preferences.
Unusual results
2 threshold-crossing signals flagged · 23 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 CritPt (AA) published 2026-09-10
Why
Observed: 0.31429 fractionPeer mean 0.04412 · peer sd 0.08179 · n 537 · families 370Directed z 3.303 · baseline z 1.564 · gap 1.739 · profile n 220.31429 fractionmeasuredobserved 2026-09-10artificialanalysis.ai ↗Evidence
Axis: CritPt (AA) · published 2026-09-10 · Published boardExact value:0.314285714285714fractionObserved: 2026-09-10T21:47:16.627Z · publication date: not recordedObservation id:aa:1f541ef3-913f-4eb2-9d07-0e93c7a9a5e3:critpt - unusually strong Terminal-Bench v4.0 (AA)
Why
Observed: 0.59596 fractionPeer mean 0.10118 · peer sd 0.15754 · n 147 · families 107Directed z 3.141 · baseline z 1.611 · gap 1.529 · profile n 220.59596 fractionmeasuredobserved 2026-09-10artificialanalysis.ai ↗Evidence
Axis: Terminal-Bench v4.0 (AA) · v4.0 · Published boardExact value:0.595959595959596fractionObserved: 2026-09-10T21:47:16.627Z · publication date: not recordedObservation id:aa:1f541ef3-913f-4eb2-9d07-0e93c7a9a5e3:terminalbenchV40
Missing coverage · 271 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 2026-11-03 · Intelligence Index v5.0 (est. = estimated from v4, not measured) · Coding Index v4.x frozen 2026-10-27 · Data: Artificial Analysis · Data: Epoch AI (CC BY)
| Variant | AA Coding | AA Intelligence |
|---|---|---|
| GPT-6 Astra (High) | 77.1 | 54.8 |
| GPT-6 Astra (Max) | 76.9 | 56.9 |
| GPT-6 Astra (Medium) | 76.7 | 51.5 |
| GPT-6 Astra (Xhigh) | 75.9 | 55.3 |
| GPT-6 Astra (Low) | 75.7 | 43.0 |
SUBSCRIPTION PLAN
GitHub Copilot
Current usage-based billing · model token cost is converted to AI Credits at 1 credit = $0.01.
Token offers by platform · 7 offers (Adjusted $/task)
Click any underlined price to see how it is estimated and where each input comes from. How we calculate adjusted cost.
7 offers within the active global filters, 3 more outside them; “price n/a” means the provider serves the model but publishes no direct token price we could collect — no other channel's price is shown in its place.
OpenRouter (4)
Prices via OpenRouter — what OpenRouter charges for each provider's endpoint, not the provider's own direct price. Source: openrouter.ai/openai/gpt-6-astra/providers, collected 2026-11-03.
| Azureconditional | globalazure | $10.00 raw in $/1M | $50.00 raw out $/1M | |
| Azureconditional | globalazure/us | $11.00 raw in $/1M | $55.00 raw out $/1M | |
| Amazon Bedrockconditional | globalamazon-bedrock/us-west-2 | $11.00 raw in $/1M | $55.00 raw out $/1M | |
| Amazon Bedrockconditional | globalamazon-bedrock/global | $10.00 raw in $/1M | $50.00 raw out $/1M |
Azure AI Foundry (1)
Direct prices from Azure AI Foundry's own price list. Source: prices.azure.com/api/retail/prices, collected 2026-11-03.
| Azure AI Foundry | global | $10.00 raw in $/1M | $50.00 raw out $/1M |
T-Systems LLM Hub (2)
Direct prices from T-Systems LLM Hub's own price list. Source: docs.llmhub.t-systems.net/models/llms/, collected 2026-11-03.
| T-Systems LLM Hub | euup to 272k inputEU | $10.86 raw in $/1M | $54.29 raw out $/1M | |
| T-Systems LLM Hub | euabove 272k inputEU | $21.71 raw in $/1M | $81.43 raw out $/1M |