Side by side · November 2026

GPT-6.2 Sol vs GPT-6.1 Terra

GPT-6.2 Sol and GPT-6.1 Terra are within three points on the Models at Work leaderboard, which we treat as a tie (64 vs 61 out of 100). On independent tests alone, GPT-6.2 Sol is ahead (69 vs 56). GPT-6.1 Terra is cheaper: 1,000 support replies cost about $5 at list price, against $10 on GPT-6.2 Sol, which is 2 times as much. On the Artificial Analysis Intelligence Index, one of the independent tests, GPT-6.2 Sol leads 57 to 51.

Updated Nov 18, 2026 · every number links to who measured it
GPT-6.2 Sol · OpenAIGPT-6.1 Terra · OpenAI
Leaderboard rank#20#26
Score (0–100)6461
Kind of workEveryday defaultEveryday default
Price per 1M tokens$2 to read · $10 to write$1 to read · $5 to write
Reads at once1M tokens (about 750,000 words)1.05M tokens (about 788,000 words)
Where you can get itOpenAI API, Amazon Bedrock, ChatGPT Plus, Pro, Enterprise and EduOpenAI API, Amazon Bedrock, Microsoft Foundry, Gemini Enterprise Agent Platform (Google Cloud), ChatGPT Plus, Pro, Business, Enterprise and Edu
Can a company host it itselfNoNo
Artificial Analysis Intelligence Index5751
Vals Finance Index56.66% (rank 27)53.32% (rank 32)
Vals Tax Agent Bench24.84% (rank 50)17.08% (rank 62)
Vals Legal Research Bench37.02% (rank 53)25.96% (rank 66)
Humanity's Last Exam, Diamond (Scale)Not measured35.70
Best forDrafting proposals and reports, Summarising long documents, Back-office tasks with several steps, Answering questions from company documentsHigh-volume back-office tasks, Filling in forms and moving data between systems, Summarising documents

Cost of 1,000 jobs

1,000 of theseGPT-6.2 SolGPT-6.1 Terra
Support repliesthe customer message, the account notes and two help articles read; a 300-word reply written$10$5
Documents processeda two-page invoice or form read; the fields pulled out$7$3.50
Calls summariseda 40-minute call transcript read; a summary and next steps written$26$13
Contracts revieweda 40-page contract read against a checklist; a memo of issues written$75$38
Drafts writtena brief and one example read; a 600-word email or proposal section written$11$5.50

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-6.2 Sol for

  • Drafting proposals and reports
  • Summarising long documents
  • Back-office tasks with several steps
  • Answering questions from company documents

The sensible OpenAI default from 17 Nov: 57 on Artificial Analysis's index, up from 55 for GPT-6.1 Sol at the same $2 and $10 list price, and within a point of GPT-6.2 Astra on Vals AI's finance test.

Caveats: The price rises on any request that feeds it more than 272,000 tokens of text at once: reading costs double and writing 1.5 times as much for the whole request, OpenAI's model page says. Weak on Vals AI's tax test (24.8% of tasks right) and legal research test (37.0%); Claude Haiku 5.5 gets 43.8% on legal research. The ChatGPT plans come from 9to5Mac's report of 17 Nov, which does not mention the Business plan; OpenAI's launch page refused automated reading. No page read on 18 Nov names GPT-6.2 Sol in Microsoft 365 Copilot, Microsoft Foundry or Google Cloud, where GPT-6.1 Sol is sold. Scores within a point of GPT-6.1 Sol, which the method treats as a tie: no user reports are scored yet, so its place rests on tests, price and where it is sold.

Choose GPT-6.1 Terra for

  • High-volume back-office tasks
  • Filling in forms and moving data between systems
  • Summarising documents

Half the list price of GPT-6.1 Sol for four points less on Artificial Analysis's index (51 against 55): the cheaper OpenAI default where the work is routine.

Caveats: Requests that feed it more than 272,000 tokens of text at once are billed at twice the input price and 1.5 times the output price, per OpenAI. The 51 is at its top effort setting, where a test task took 13.9 minutes in Artificial Analysis's run. OpenAI sells it for operating software on screen like a person would; no independent test of that was found. The ChatGPT plans are listed from our researcher's reading of OpenAI's help page, which blocked automated reading this run. Down from 14th to 25th: Vals AI's tests now count, and it gets 53.3% right on finance work, 17.1% on tax and 26.0% on legal research, among the lowest readings on this board.

What people running them say

GPT-6.2 Sol: The launch thread on Hacker News, a developer forum, drew 1,283 points and 798 comments in a day, and the early replies are mixed: one commenter calls Sol 'a marginal step forward' after a day, another reports Astra refusing a task on hardware they own, others praise the speed against Gemini 4 Carbon. No reports yet from operations teams.

Questions people ask

Which is better, GPT-6.2 Sol or GPT-6.1 Terra?

GPT-6.2 Sol and GPT-6.1 Terra are within three points on the Models at Work leaderboard, which we treat as a tie (64 vs 61 out of 100). On independent tests alone, GPT-6.2 Sol is ahead (69 vs 56). GPT-6.1 Terra is cheaper: 1,000 support replies cost about $5 at list price, against $10 on GPT-6.2 Sol, which is 2 times as much. On the Artificial Analysis Intelligence Index, one of the independent tests, GPT-6.2 Sol leads 57 to 51.

When should I choose GPT-6.2 Sol over GPT-6.1 Terra?

Choose GPT-6.2 Sol for drafting proposals and reports, summarising long documents, back-office tasks with several steps, answering questions from company documents. The sensible OpenAI default from 17 Nov: 57 on Artificial Analysis's index, up from 55 for GPT-6.1 Sol at the same $2 and $10 list price, and within a point of GPT-6.2 Astra on Vals AI's finance test.

When should I choose GPT-6.1 Terra over GPT-6.2 Sol?

Choose GPT-6.1 Terra for high-volume back-office tasks, filling in forms and moving data between systems, summarising documents. Half the list price of GPT-6.1 Sol for four points less on Artificial Analysis's index (51 against 55): the cheaper OpenAI default where the work is routine.

Which is cheaper, GPT-6.2 Sol or GPT-6.1 Terra?

GPT-6.2 Sol costs $2 per million tokens it reads (input) and $10 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-6.1 Terra costs $1 per million tokens it reads (input) and $5 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-6.2 Sol and GPT-6.1 Terra?

At list price: 1,000 support replies cost $10 on GPT-6.2 Sol and $5 on GPT-6.1 Terra; 1,000 documents processed cost $7 on GPT-6.2 Sol and $3.50 on GPT-6.1 Terra; 1,000 calls summarised cost $26 on GPT-6.2 Sol and $13 on GPT-6.1 Terra; 1,000 contracts reviewed cost $75 on GPT-6.2 Sol and $38 on GPT-6.1 Terra; 1,000 drafts written cost $11 on GPT-6.2 Sol and $5.50 on GPT-6.1 Terra. 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.