Side by side · November 2026

GPT-6 Luna vs GPT-6 Astra

GPT-6 Luna scores higher on the Models at Work leaderboard (71 vs 59 out of 100). On independent tests alone, GPT-6 Astra is ahead (69 vs 54). GPT-6 Luna is cheaper: 1,000 support replies cost about $0.50 at list price, against $50 on GPT-6 Astra, which is 100 times as much. On the Artificial Analysis Intelligence Index, one of the independent tests, GPT-6 Astra leads 57 to 28.

Updated Nov 18, 2026 · every number links to who measured it
GPT-6 Luna · OpenAIGPT-6 Astra · OpenAI
Leaderboard rank#9#27
Score (0–100)7159
Kind of workHigh-volume workHardest problems
Price per 1M tokens$0.10 to read · $0.50 to write$10 to read · $50 to write
Reads at once1M tokens (about 750,000 words)1M tokens (about 750,000 words)
Where you can get itOpenAI API, Amazon Bedrock, Microsoft Foundry, Gemini Enterprise Agent Platform (Google Cloud)OpenAI API, Amazon Bedrock, Microsoft Foundry, Gemini Enterprise Agent Platform (Google Cloud), ChatGPT Pro, Business and Enterprise
Can a company host it itselfNoNo
Artificial Analysis Intelligence Index2857
Humanity's Sixth Sense (Scale)21.0053.60
Vals Finance Index53.05% (rank 33)55.64% (rank 30)
Vals Tax Agent Bench19.95% (rank 59)20.72% (rank 56)
Vals Legal Research Bench30.29% (rank 59)39.42% (rank 40)
Professional Reasoning Benchmark - Legal (Scale)42.8548.36
Humanity's Last Exam, Diamond (Scale)Not measured60.60
FrontierMath Erdős (Epoch)Not measured3% (2 of 68)
Remote Labor Index (Scale)Not measured20.83% of projects automated
Professional Reasoning Benchmark - Finance (Scale)Not measured47.54
Best forSimple extraction from forms and emails, Short routine replies, Sorting messagesProblems where a wrong answer costs more than the bill, Research-grade analysis, Hard scientific and mathematical questions

Cost of 1,000 jobs

1,000 of theseGPT-6 LunaGPT-6 Astra
Support repliesthe customer message, the account notes and two help articles read; a 300-word reply written$0.50$50
Documents processeda two-page invoice or form read; the fields pulled out$0.35$35
Calls summariseda 40-minute call transcript read; a summary and next steps written$1.30$130
Contracts revieweda 40-page contract read against a checklist; a memo of issues written$3.75$375
Drafts writtena brief and one example read; a 600-word email or proposal section written$0.55$55

Worked out from each vendor’s list price and a fixed size for each job. A product built on a model charges its own price on top. See what every model costs for the same jobs.

Choose GPT-6 Luna for

  • Simple extraction from forms and emails
  • Short routine replies
  • Sorting messages

OpenAI's cheapest model, at the same list price as Claude Haiku 5.5 but eight points behind it on Artificial Analysis's index (28 against 36).

Caveats: It ranks 9th largely because price is 30% of the board's score. Its test results are low: 28 on Artificial Analysis's index and, on Vals AI's tests, 53.1% right on finance work, 20.0% on tax and 30.3% on legal research. Users of Haiku 5.5 report it is the noticeably smarter of the two at this price. The release tracker records it as the model behind ChatGPT Free and Go; OpenAI's own page could not be read this run, so ChatGPT is not listed below.

Choose GPT-6 Astra for

  • Problems where a wrong answer costs more than the bill
  • Research-grade analysis
  • Hard scientific and mathematical questions

Superseded on 17 Nov by GPT-6.2 Astra, which lists 20% lower ($8 and $40 against $10 and $50) and scores 62 against 57 on Artificial Analysis's index. Still sold; OpenAI gives no retirement date.

Caveats: The price doubles on any request that feeds it more than 272,000 tokens of text at once, such as a stack of long documents. The slowest of the top-tier models in Artificial Analysis's speed measurement. In ChatGPT it is sold as GPT-6 Pro, on the Pro, Business and Enterprise plans; this is from our researcher's reading of OpenAI's help page, which blocked automated reading this run. Now the most expensive model here and no longer OpenAI's most capable; a team paying by usage should ask its vendor when it moves to GPT-6.2 Astra.

What people running them say

GPT-6 Astra: The launch drew 2026's largest thread about a model on Hacker News, a developer forum, and the stories that followed were about what it can do rather than what it costs: an Enigma-coded message unsolved since 2005, a First World War cipher, a driving test.

Questions people ask

Which is better, GPT-6 Luna or GPT-6 Astra?

GPT-6 Luna scores higher on the Models at Work leaderboard (71 vs 59 out of 100). On independent tests alone, GPT-6 Astra is ahead (69 vs 54). GPT-6 Luna is cheaper: 1,000 support replies cost about $0.50 at list price, against $50 on GPT-6 Astra, which is 100 times as much. On the Artificial Analysis Intelligence Index, one of the independent tests, GPT-6 Astra leads 57 to 28.

When should I choose GPT-6 Luna over GPT-6 Astra?

Choose GPT-6 Luna for simple extraction from forms and emails, short routine replies, sorting messages. OpenAI's cheapest model, at the same list price as Claude Haiku 5.5 but eight points behind it on Artificial Analysis's index (28 against 36).

When should I choose GPT-6 Astra over GPT-6 Luna?

Choose GPT-6 Astra for problems where a wrong answer costs more than the bill, research-grade analysis, hard scientific and mathematical questions. Superseded on 17 Nov by GPT-6.2 Astra, which lists 20% lower ($8 and $40 against $10 and $50) and scores 62 against 57 on Artificial Analysis's index. Still sold; OpenAI gives no retirement date.

Which is cheaper, GPT-6 Luna or GPT-6 Astra?

GPT-6 Luna costs $0.10 per million tokens it reads (input) and $0.50 per million tokens it writes (output) on OpenAI's list price (OpenAI API pricing, read Nov 18, 2026). A token is about three-quarters of a word. GPT-6 Astra costs $10 per million tokens it reads (input) and $50 per million tokens it writes (output) on OpenAI's list price (OpenAI API pricing, read Nov 18, 2026). A token is about three-quarters of a word.

What do 1,000 jobs cost on GPT-6 Luna and GPT-6 Astra?

At list price: 1,000 support replies cost $0.50 on GPT-6 Luna and $50 on GPT-6 Astra; 1,000 documents processed cost $0.35 on GPT-6 Luna and $35 on GPT-6 Astra; 1,000 calls summarised cost $1.30 on GPT-6 Luna and $130 on GPT-6 Astra; 1,000 contracts reviewed cost $3.75 on GPT-6 Luna and $375 on GPT-6 Astra; 1,000 drafts written cost $0.55 on GPT-6 Luna and $55 on GPT-6 Astra. A product built on either model charges its own price on top.

Scores come from the Models at Work leaderboard: Score is 0 to 100 and computed, not typed. 40% is independent testing (Artificial Analysis, Arena, Scale, Epoch, Vals and others; each test is scaled against the best score on this board, and tests of real work, such as finished freelance projects or professional tasks, count double the exams). 30% is price: the vendor's list price for a typical mix of reading and writing, on a fixed scale from $0.05 to $60 per million tokens, so a model that costs a fifth as much gains real ground. 15% is what people report after running it, from Signals and linked threads. 15% is fit: how much text it can take in at once and where a business can get it (the products and clouds that carry it), with a small credit for open weights. A missing component drops out and the rest are reweighted. A model with no independent test yet is provisional and ranks below every measured one. Within three points is a tie. Vendor-published figures are labelled and never counted. Prices are vendor list prices where published; a typical mix assumes three parts reading to one part writing.