AI Model Release Tracker

GPT-5.6 Terra

Released

GPT-5.6 Terra is an AI model released by OpenAI on Friday, Jun 26 2026, the same day as GPT-5.6 Sol. It has a 1.05M token context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider.. Benchmark results (shown below) cover BullshitBench v2, Gray Swan IPI, SWE-Bench Pro, CursorBench 4.0, DeepSWE 1.1, BenchCAD, and 19 more.

API pricing

Up to 272K input tokens
InputWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it.
$2.00
Cached inputA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again.
$0.20
Cache writeA one-off charge for storing text so later requests can reuse it at the cheaper cached rate.
$2.50
OutputWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one.
$12.00
Over 272K input tokens
InputWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it.
$4.00
Cached inputA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again.
$0.40
Cache writeA one-off charge for storing text so later requests can reuse it at the cheaper cached rate.
$5.00
OutputWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one.
$18.00
  • Reasoning or thinking is supported.
USD per 1M tokensEvery price here is for one million tokens. A token is roughly three-quarters of a word, so a million tokens is about 750,000 words of text.Verified October 19, 2026Read from developers.openai.com. Click the check to open the source.

Available from

OpenAI—flex$1.00$6.001M
OpenAI——$2.00$12.001M
Azure——$2.00$12.001M
Azureeu—$2.20$13.201M
Azureus—$2.20$13.201M
Amazon Bedrockus-east-1—$2.20$13.201M
OpenAI—fast$4.00$24.001M
USD per 1M tokensEvery price here is for one million tokens. A token is roughly three-quarters of a word, so a million tokens is about 750,000 words of text.Checked November 9, 2026Third-party rates from openrouter.ai, not the lab’s own list price.

Benchmarks

Coding

SWE-Bench ProAgentic coding — Can the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better.
63.4%
#14 of 42
CursorBench 4.0Agentic coding — Cursor's own test of coding agents on ambiguous, multi-file tasks taken from real Cursor sessions — editing, refactoring, investigating a codebase, understanding what the user meant, managing jobs and following a design. Cursor runs each model at several reasoning efforts; each release here carries the score of its best listed effort. Scores aren't comparable with earlier CursorBench versions. Higher is better.via CursorBench
41.3%
#13 of 18
DeepSWE 1.1Agentic coding — Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better.
69.6%
#15 of 42
BenchCADCAD programming — geometric overlap of generated CAD parts without tool access
62.3%without tools
78.2%with tools
without tools
#3 of 3
with tools
#3 of 4

Terminal & CLI

Frontier-Bench v0.1Agentic computer work — A hard, ever-evolving set of real computer tasks — coding, system administration, data work, and more — that an AI agent has to complete on its own. Run by the Harbor / Laude Institute team as the successor to Terminal-Bench (v0.1 is the first release of the task set). The score is the share of tasks solved. Higher is better.
20.8%
#5 of 9
Terminal-Bench 4.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Version 4.0 recalibrated how much time, CPU and memory each task gets, removed eight tasks and fixed nineteen, so fewer runs fail for reasons that have nothing to do with the model. Scores are not comparable with earlier versions. Higher is better.via Terminal-Bench
21.52%
#27 of 36
Terminal-Bench 2.1Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better.
87.4%
#10 of 39

Agentic & tool use

ToolathlonGeneral tool use — Tests how well the AI uses everyday real-world tools and apps to get things done. Higher is better.
53.1%
#6 of 11
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better.via BenchLM
87.5%
#9 of 35
Agent's Last ExamAgentic computer use — A hard set of desktop and operating-system tasks an AI agent has to finish by looking at the screen and working the machine itself. The score is the share it passes outright — partial credit does not count. Higher is better.
50.4%pass@1
#5 of 15
AutomationBenchBusiness workflows — Tests whether the AI can run real multi-step business workflows — the kind of end-to-end office processes companies want to automate — from start to finish. Higher is better.
15.2%
#28 of 32

Reasoning & science

ARC-AGI-3Novel problem-solving — The third generation of the ARC-AGI series: instead of static puzzles, the AI is dropped into small interactive game-like environments it has never seen and has to figure out the rules and solve them on its own. Higher is better.
0.8%
#4 of 5
ARC-AGI-2Abstract reasoning — Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better.via BenchLM
83.9%
#14 of 41
FrontierMathAdvanced math — The rebuilt edition of FrontierMath's hardest tier — research-level maths of the kind professional mathematicians work on. It is a different question set from the first Tier 4, and scores on it run far higher, so read the two as separate tests rather than progress. Higher is better.
68.3%Tier 4 (v2)
84.9%Tiers 1–3 (v2)
Tier 4 (v2)
#3 of 4
Tiers 1–3 (v2)
#2 of 3
GeneBench-ProBiology — Real genomics and biomedical analyses done end to end: the AI gets a messy dataset and a question, and has to work through the chain of statistical decisions to a verifiable answer — the job a computational biologist does before a research or clinical decision gets made. Higher is better.
23.3%
#3 of 4
MedChemBench (Internal)Chemistry — OpenAI's own drug-discovery test: reading chemical structures, predicting how potent or toxic a compound will be, choosing between candidate molecules, and planning a synthesis route — the everyday judgement calls of a medicinal chemist. Higher is better.
35%
#3 of 4
LifeSciBenchReasoning — performance on research tasks graded by life sciences experts
56%
#3 of 4
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better.
92.9%
#11 of 100

Healthcare

HealthBench ProfessionalHealth — official OpenAI grading with the response-length penalty applied
57.7%OpenAI grading, length-adjusted
#5 of 6

Multimodal

GDP.PDFDocument comprehension — Real professional PDFs — filings, reports, technical documents — with questions an expert in that field would ask. Tests whether the AI reads the page as a document, layout and figures included, rather than as loose text. Higher is better.
24.7%
#8 of 10
MMMU-ProMultimodal reasoning — multimodal understanding and reasoning with access to tools
82%with tools
80.7%
with tools
#4 of 8
#12 of 29

Long context

MRCR v2 (8-needle)Long context — mean match ratio for eight needles within the indicated context band
89.6%256K–512K
72.5%512K–1M
256K–512K
#3 of 6
512K–1M
#4 of 6

Robustness

BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better.
54%
#35 of 98
Gray Swan IPIPrompt injection robustness — Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. Gray Swan's indirect prompt injection benchmark measures how often such an attack succeeds when the attacker gets a single try. Lower is better.
5.4%k = 1
26%k = 10
30.4%k = 15
k = 1
#8 of 13
k = 10
#8 of 13
k = 15
#10 of 15

Community preference

threejsevalCommunity preference (Three.js) — Every model gets the same prompt — "the Eiffel Tower", "a glass fishbowl", "a robot arm picking toys into a box" — and builds a 3D scene in Three.js. Real people then see two scenes side by side, names hidden, and vote for the one they prefer. The votes become a chess-style Elo rating on threejseval.com, averaged across all the prompts. It measures whether the scene looks and moves right to a human eye, not whether the code passes a test. Higher is better.
1429
#18 of 29

Source: CursorBench, retrieved 28 September 2026 · Source: Terminal-Bench, retrieved 30 August 2026 · Source: BenchLM, retrieved 24 August 2026. Other sources are identified on the linked benchmark pages.

Compare GPT-5.6 Terra with

GPT-5.6 Terra

Suggested comparisons

GPT-5.6 TerravsGPT-6.1 TerraGPT-5.6 TerravsClaude Fable 5.2GPT-5.6 TerravsGemini 4 CarbonGPT-5.6 TerravsMuse EmberGPT-5.6 TerravsGrok 4.7GPT-5.6 TerravsDeepSeek-V4.1-Flash-1017GPT-5.6 TerravsMistral Large 4GPT-5.6 TerravsKimi K3.1 ProGPT-5.6 TerravsGLM-5.3-FlashGPT-5.6 TerravsQwen3.8-Max-0902GPT-5.6 TerravsNemotron 3.5 Bolt E4B 4GB

About

GPT-5.6 Terra was announced in the June 2026 GPT-5.6 preview as the balanced model for everyday work, between flagship Sol and the lower-cost Luna tier. OpenAI positioned it around capability and efficiency for frequent professional tasks. Initial access was limited to trusted partners, with general availability coming later for the family.

Its API offered a 1,050,000-token context window and configurable reasoning, preserving substantial input capacity in the middle tier. Terra's role roughly corresponded to the mini tier of earlier GPT-5 releases. GPT-6.1 Terra followed in October 2026 with an emphasis on visual reasoning, computer use and writing; that later release was separate from the original GPT-5.6 preview and rollout.

Frequently asked questions

GPT-5.6 Terra was released by OpenAI on Friday, Jun 26 2026.

All OpenAI releases

49 tracked

2022

1 release
GPT-3.5
Nov 30 2022