Skip to content

OpenAI Proprietary Released Oct 26, 2026 Updated

GPT-6.1 Terra

ToolsGuide Scores, rankings, test results and price.

Model summary

  • Coding #12 / 151

    521 / 1,000

    ToolsGuide Score· votes only

  • Agents #10 / 57

    535 / 1,000

    ToolsGuide Score· votes 550, tests 518

  • Price per 1M tokens

    In $1.00· Out $5.00

    $1.00

    Input · median coding model $0.75

Summary

GPT-6.1 Terra is OpenAI's model, released Oct 26, 2026. It's ranked in 2 categories and does best at coding: #12 of 151, with a ToolsGuide Score of 521 against a median of 318.

It also ranks #10 of 57 for agents (535).

Its coding score uses votes only, because it has published fewer than two of the tests used for that category.

It costs $1.00 per million input tokens and $5.00 per million output tokens, about 1.3× the median coding model ($0.75).

It has published results on 8 tests and has the top score on 1 of them, including Agents' Last Exam.

Specifications

Creator
OpenAI
Licence
Proprietary
Released
Oct 26, 2026
Context window
1.1M tokens
Input price
$1.00 / 1M
Output price
$5.00 / 1M
Tests reported
8
Settings ranked
GPT-6.1 Terra (Max)

Model comparison

Against the ten best coding models.

Coding score

ToolsGuide Score out of 1,000 · Higher is better

Agents score

ToolsGuide Score out of 1,000 · Higher is better

Input price

USD per 1M input tokens · Lower is better

Leaderboards

Where GPT-6.1 Terra sits among the top 20 in each category.

Coding

#12 of 151 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model

Full coding leaderboard →

Agents

#10 of 57 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model

Full agents leaderboard →

By task

Scored from votes on each kind of prompt alone, on the same 1,000-point scale.

Score against price

Coding · the 10 priced models ranked closest · up and to the left is better value

Coding

GPT-6.1 Terra (Max) · hover a bar for its rank

Test results

Every test GPT-6.1 Terra has a published result on, out of 100%, with its rank among the models that took it.

  • Terminal-Bench 4.0

    #11 / 31

    Terminal-Bench 4.0 evaluates AI agents on real-world work in terminal and command-line containerized environments across 66 tasks, with emphasis on science-adjacent and frontier engineering problems. Relative to earlier Terminal-Bench releases, 4.0 increases timeouts and adaptively raises RAM/CPU on selected tasks to reduce harness and resource confounds.

    50.3%

    Self-reported · In the coding score· In the agents score

  • Agents' Last Exam

    #1 / 26

    Agents' Last Exam is a challenging benchmark for AI agents on hard, long-horizon tasks that test sustained reasoning, planning, and tool use, reported with and without tool access.

    60.0%

    Self-reported · In the agents score

  • HealthBench Hard

    #6 / 25

    A challenging variation of HealthBench that evaluates large language models' performance and safety in healthcare through 5,000 multi-turn conversations with particularly rigorous evaluation criteria validated by 262 physicians from 60 countries

    31.4%

    Self-reported

  • HealthBench Professional

    #7 / 20

    HealthBench Professional evaluates model capability and safety for clinician use cases using real clinician-style chats and physician-authored grading rubrics.

    62.7%

    Self-reported

  • HealthBench

    #11 / 15

    An open-source benchmark for measuring performance and safety of large language models in healthcare, consisting of 5,000 multi-turn conversations evaluated by 262 physicians using 48,562 unique rubric criteria across health contexts and behavioral dimensions

    55.1%

    Self-reported

  • Terminal-Bench-Science 0.1

    #5 / 10

    Terminal-Bench-Science 0.1 is a Stanford-led community benchmark of 70 tasks drawn from scientific research workflows across the life, physical, earth, mathematical, and engineering sciences. Tasks are authored and reviewed by scientists and researchers; scores are typically reported as accuracy with relatively large standard error due to strongly bimodal per-task outcomes.

    58.3%

    Self-reported

  • HealthBench Consensus

    #3 / 6

    HealthBench Consensus is a HealthBench subset focused on questions where physician-created rubric criteria have especially high agreement, measuring healthcare performance and safety on consensus-evaluable conversations.

    95.1%

    Self-reported

  • MentalHealthBench

    #2 / 2

    MentalHealthBench is an open benchmark developed with mental health experts for measuring how AI systems respond in realistic mental health conversations. It consists of 1,215 synthetic conversations covering diverse scenarios ranging from daily well-being topics to urgent mental health emergencies, scored with clinician-authored rubric criteria.

    55.5%

    Unverified