GPT-5.6 Terra (max)

July 9, 2026Last synced Aug 1, 2026, 12:19 AM1050K context

Human Frontier

—

Human-calibrated frontier signal, backed by Arena-style preference evidence and separate from raw AgMoBench benchmark composite scores.

Blended Price

$4.50/M

Input Price

$2.00/M

Output Price

$12.00/M

Speed

132 tok/s

TTFT

75.09s

Benchmark Scores

Intelligence Index

Performance Radar

GPT-5.6 Terra (max)

Field Average

External Benchmarks

AA-Omniscience Accuracy

How GPT-5.6 Terra (max) Compares

Axes

X Axis

Y Axis

Bubble Size

Filters

Blended Price (USD)$0.00 – $37.5

AgMoBench Overall≥ 1.8

Providers

ai2ai21-labsalibabaanthropicarceeawsazurebaidu

Show quadrants

anthropic

openai

mistral

azure

cohere

meta

ai21-labs

inclusionai

google

ai2

ibm

alibaba

upstage

nvidia

aws

kimi

nous-research

thinking-machines

minimax

stepfun

tencent

deepseek

zai

multiversecomputing

xiaomi

xai

deepcogito

sarvam

kwaikat

baidu

swiss-ai-initiative

bytedance_seed

inception

reka-ai

arcee

perplexity

Bubble size = Context Window

8191.00

2000000.00

Compare with other models

ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · GPT-5.6 Terra (Max) · effort max · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:openai-gpt-5-6-terra-max

View run source

Source metadata

{
  "provider": "OpenAI",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "openai-gpt-5-6-terra",
  "modelNotes": null,
  "modelsEtag": "W/\"2fc19b6caba8b52765ca17eab04fc437\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"9485c7ef206d9b12cdfdec6a631df56b\"",
  "upstreamModelId": "openai-gpt-5-6-terra-max",
  "environmentCount": 25,
  "modelReleaseDate": "2026-07-09T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 7918.31,
  "providerModelIdPublished": false
}

Evidence observed 2026-07-31

0.8 / 100

ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · GPT-5.6 Terra (Max) · effort max · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:openai-gpt-5-6-terra-max

View run source

Source metadata

{
  "provider": "OpenAI",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "openai-gpt-5-6-terra",
  "modelNotes": null,
  "modelsEtag": "W/\"2fc19b6caba8b52765ca17eab04fc437\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"9485c7ef206d9b12cdfdec6a631df56b\"",
  "upstreamModelId": "openai-gpt-5-6-terra-max",
  "environmentCount": 25,
  "modelReleaseDate": "2026-07-09T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 7918.31,
  "providerModelIdPublished": false
}

Evidence observed 2026-07-31

0.8 / 100

ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · GPT-5.6 Terra (Max) · effort max · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:openai-gpt-5-6-terra-max

View run source

Source metadata

{
  "provider": "OpenAI",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "openai-gpt-5-6-terra",
  "modelNotes": null,
  "modelsEtag": "W/\"cfc9b87c645d3ef2103e359fd0f9f521\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"0d65f6e0efe0d5cae15e8e2fe5a0994b\"",
  "upstreamModelId": "openai-gpt-5-6-terra-max",
  "environmentCount": 25,
  "modelReleaseDate": "2026-07-09T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 7918.31,
  "providerModelIdPublished": false
}

Evidence observed 2026-07-30

0.8 / 100

ARC-AGI-3 Public Demoarc_agi

v3 · public-demo · GPT-5.6 Terra (Max) · effort max · 1 attempt · 5x-human-baseline-median-per-level · arc-agi-3:public-demo · record v3_Semi_Private:openai-gpt-5-6-terra-max

View run source

Source metadata

{
  "provider": "OpenAI",
  "modelType": "CoT",
  "modelsUrl": "https://arcprize.org/media/data/models.json",
  "modelGroup": "openai-gpt-5-6-terra",
  "modelNotes": null,
  "modelsEtag": "W/\"bbdf5725ef7a703a7f0970e913262b6f\"",
  "scoreMetric": "relative-human-action-efficiency",
  "evaluationsUrl": "https://arcprize.org/media/data/evaluations.json",
  "evaluationsEtag": "W/\"6529094085f9ca7ce5f3c2e1957d3b9c\"",
  "upstreamModelId": "openai-gpt-5-6-terra-max",
  "environmentCount": 25,
  "modelReleaseDate": "2026-07-09T00:00:00.000Z",
  "upstreamDatasetId": "v3_Semi_Private",
  "actionBudgetPolicy": "5x-human-baseline-median-per-level",
  "technicalReportUrl": "https://arcprize.org/media/ARC_AGI_3_Technical_Report.pdf",
  "catalogMatchAliases": [],
  "agentHarnessPublished": false,
  "verificationAuthority": "ARC Prize Foundation",
  "upstreamRunIdPublished": false,
  "actualEvaluationCostUsd": 7918.31,
  "providerModelIdPublished": false
}

Evidence observed 2026-07-24

0.8 / 100

Terminal-Bench 2.1terminal_bench

v2.1 · official-leaderboard · GPT-5.6 Terra (max) · harness codex@0.144.1 · effort max · 5 attempts · harbor:terminal-bench/terminal-bench-2-1 · provider openai/gpt-5.6-terra · record leaderboard/submissions/2026-07-11-openai-gpt-5-6-terra-max-codex.json · run 84f460e2-f7f8-5249-8e63-d58b197968c7

View run source

Source metadata

{
  "passAt2": 0.8539,
  "passAt3": 0.8753,
  "passAt4": 0.8876,
  "passAt5": 0.8989,
  "taskCount": 89,
  "actualTokens": {
    "output": 8707506,
    "cachedInput": 864130644,
    "uncachedInput": 29803660
  },
  "datasetPackage": "terminal-bench/terminal-bench-2-1",
  "leaderboardUrl": "https://www.tbench.ai/leaderboard/terminal-bench/2.1",
  "pullRequestUrl": "https://github.com/harbor-framework/terminal-bench-2-1/pull/115",
  "agentDisplayUrl": "https://openai.com/codex/",
  "modelDisplayUrl": "https://developers.openai.com/api/docs/models/gpt-5.6-terra",
  "actualTrialCount": 445,
  "agentOrganization": "OpenAI",
  "modelOrganization": "OpenAI",
  "actualTotalCostUsd": 421.15,
  "rewardHacksPercent": 0.22,
  "accuracyStandardError": 1.25,
  "submissionDownloadUrl": "https://raw.githubusercontent.com/harbor-framework/terminal-bench-2-1/main/leaderboard/submissions/2026-07-11-openai-gpt-5-6-terra-max-codex.json",
  "disqualifiedTrialCount": 1,
  "expectedAttemptsPerTask": 5,
  "sourceFilterReasoningEffort": "max",
  "actualAverageTrialDurationSeconds": 432.8
}

Evidence observed 2026-07-11

78.4 / 100

Terminal-Bench 2.1terminal_bench

v2.1 · official-leaderboard · GPT-5.6 Terra (max) · harness codex@0.144.0 · effort max · 5 attempts · harbor:terminal-bench/terminal-bench-2-1 · provider gpt-5.6-terra · record leaderboard/submissions/2026-07-10-gpt-5-6-terra-max-codex.json · run 622b427f-0ddc-54db-b64b-90960667e6be

View run source

Source metadata

{
  "passAt2": 0.8494,
  "passAt3": 0.8899,
  "passAt4": 0.9101,
  "passAt5": 0.9213,
  "taskCount": 89,
  "actualTokens": {
    "output": 8273026,
    "cachedInput": 791614561,
    "uncachedInput": 31612623
  },
  "datasetPackage": "terminal-bench/terminal-bench-2-1",
  "leaderboardUrl": "https://www.tbench.ai/leaderboard/terminal-bench/2.1",
  "pullRequestUrl": "https://github.com/harbor-framework/terminal-bench-2-1/pull/106",
  "agentDisplayUrl": "https://openai.com/codex/",
  "modelDisplayUrl": "https://developers.openai.com/api/docs/models/gpt-5.6-terra",
  "actualTrialCount": 445,
  "agentOrganization": "OpenAI",
  "modelOrganization": "OpenAI",
  "actualTotalCostUsd": 401.03,
  "rewardHacksPercent": 7.19,
  "accuracyStandardError": 1.54,
  "submissionDownloadUrl": "https://raw.githubusercontent.com/harbor-framework/terminal-bench-2-1/main/leaderboard/submissions/2026-07-10-gpt-5-6-terra-max-codex.json",
  "disqualifiedTrialCount": 32,
  "expectedAttemptsPerTask": 5,
  "sourceFilterReasoningEffort": "max",
  "actualAverageTrialDurationSeconds": 421.6
}

Evidence observed 2026-07-10

74.4 / 100