GPT-⁠6.1 Sol vs GPT-⁠6.1 Terra.

GPT-⁠6.1 Sol scores higher, 55 against 51, but GPT-⁠6.1 Terra is 24% cheaper per task.

OpenAI
Data from 13 November 2026.

Which is better?

GPT-⁠6.1 Sol scores higher on Artificial Analysis's Intelligence Index, 55 against 51. It is 5th of the 58 models it scores, and GPT-⁠6.1 Terra 8th.

On the four coding and reasoning tests, GPT-⁠6.1 Sol wins HLE Diamond and CritPt v2, GPT-⁠6.1 Terra wins FrontierCode 2.0, and they are level on Terminal-⁠Bench 4.0.

Per task, GPT-⁠6.1 Terra is 24% cheaper and faster too, $0.96 against $1.27 and 14.6 minutes against 23.3 minutes.

Per token, OpenAI charges $2 per million input tokens and $10 per million output tokens for GPT-⁠6.1 Sol, and $1 and $5 for GPT-⁠6.1 Terra. Both read up to 1.05 million tokens at once.

  • Choose GPT-⁠6.1 Sol if

    • you want the higher score, 55 against 51
    • you want it for reasoning, it wins HLE Diamond and CritPt v2
  • Choose GPT-⁠6.1 Terra if

    • the cost of each task matters, $0.96 against $1.27
    • you want it to take less time, 14.6 minutes against 23.3 per task

At a glance

FigureGPT-⁠6.1 SolOpenAIGPT-⁠6.1 TerraOpenAI
ScoreArtificial Analysis's index55Better5th of 58518th of 58
Cost per task$1.2729th of 51$0.96Better24th of 51
Time per task23.3 min32nd of 5014.6 minBetter25th of 50
Input pricePer million tokens$2$1Better
Output pricePer million tokens$10$5Better
Context1.05 million1.05 million
WeightsClosedClosed
Effort measuredEach one's highestMaxMax
Released29 Sept 202626 Oct 2026

The score, the cost and the time per task and the tests from Artificial Analysis, read on 13 November 2026 with each model at its highest effort. The price, the context and the release date from OpenAI's page. The table of the 58.

Their tests

Coding

FrontierCode 2.0 Changes to real open-⁠source projects.

  • GPT-⁠6.1 Sol40.6%
  • GPT-⁠6.1 Terra42.3%

Terminal-⁠Bench 4.0 Complex work in the terminal, on its own.

  • GPT-⁠6.1 Sol56.1%
  • GPT-⁠6.1 Terra55.6%

Reasoning

HLE Diamond Expert-⁠level questions.

  • GPT-⁠6.1 Sol58.8%
  • GPT-⁠6.1 Terra47.3%

CritPt v2, hard subset Physics research problems.

  • GPT-⁠6.1 Sol69.5%
  • GPT-⁠6.1 Terra68.0%

Questions.

  • Which one is cheaper?

    Per task, GPT-⁠6.1 Terra, with $0.96 against $1.27 on the tasks of Artificial Analysis's index. Per token, GPT-⁠6.1 Terra, with $1 and $5 per million input and output tokens against $2 and $10.

  • Which one reads more text at once?

    Both read up to 1.05 million tokens at once.

  • Can they run on your own servers?

    No. Neither has its weights published, so they are used through OpenAI or whoever offers them.

  • Which one for your company's software?

    It depends on the job. We cover it in “Which AI Model to Use to Build Your Company's Software”.

Let's talk.

Tell us what you need and one of the partners who write the code gets back to you.