Skip to content

OpenAI · Chat

GPT-5.6 Terra

OpenAI 🇺🇸ChatGPT familyOne of its sources says the weights aren't publicly available.The maker currently lists 11 Jan 2028 as the deprecation date. Plans can change.

Newer version: GPT-6.1 Terra. We compared release dates and version names in our catalogue.

From Venice's listing:
GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic tasks where capability and cost need to be balanced.
llminfo IQ
135.7
Maker's price
$4.50 blended / 1M
Max context
1.1M
Listings
119

Evidence and sources

llminfo IQ 135.7, ranked among chat models. From 329 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 120.9, 95% interval 116–126. From 27 benchmark families across 13 sources. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedGood value (60.4). Cheaper per task than its benchmark results predict. From 52 benchmarks with measured task costs. Plenty of data behind it.How Value for money worksYap score: tokens used per coding task vs. models with the same resultsTypical (48 ±10). Generates about as many tokens as models with similar coding results. Measured at max effort. A fair amount of data behind it. By effort: default 54 · low 33 · medium 38 · high 44 · max 48.Median 39,617 output tokens per task at max effort.How the Yap score worksReleased 9 Jul 2026 Training-data cutoff, as its sources state it Maker HQ: US (according to OpenAI's own website)
All rankings: #80 on OpenRouter this month #85 on OpenRouter today #92 on OpenRouter this week #406 on NanoGPT recentlySources: OpenAI API data, Writer Pricing, LiteLLM data, Models.dev data, AI/ML API data, OpenRouter data docs, Venice.ai data, llminfo researchPrimary data from OpenAI API from Writer Pricing: name, variant from LiteLLM: deprecation date from Models.dev: weights availability from AI/ML API: primary mode from OpenRouter: knowledge cutoff from Venice.ai: description from llminfo research: release date
Tags from its sources:instructreasoningtoolsvisiondocumentlong-contextgeneral-purposeefficient

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Trade-offs

No open weights

The weights aren't public, so you can't run it yourself.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 10 maker's prices.

Input & output

as stated by the model's providers
Text
Images
Files
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt cachingPDF inputWeb searchBatch API

Listings

 OpenAIgpt-5.6-terraSources: GenAI Prices data, LiteLLM data, Models.dev data, OpenAI API data922K$2.50cache read $0.25batch $1.00$15.00cache write $3.125batch $6.00——
 Xxapigpt-5.6-terraSource: Models.dev data1.1M$0.1231cache read $0.0123$0.7385cache write $0.1538——
 Jzstokengpt-5.6-terraSource: Models.dev data1.1M$0.2335cache read $0.0234$1.40cache write $0.3503——
 Kunavogpt-5-6-terraSource: Models.dev data1.1M$0.70cache read $0.07$4.20cache write $0.875——
 Koroutergpt-5.6-terraSource: Models.dev data1.1M$0.74cache read $0.074$4.44cache write $0.925——
 Nous Portalopenai/gpt-5.6-terra:batch · batchSource: Nous Portal Inference Gateway data1.1M$1.00cache read $0.10$6.00——
 OpenRouterInference by OpenAIopenai/gpt-5.6-terra · flexSource: OpenRouter data docs922K$1.00cache read $0.10$6.00cache write $1.251072,141ms
 Vercelopenai/gpt-5.6-terra-batch · batchSource: Vercel AI Gateway data1.1M$1.00cache read $0.10$6.00——
 Outerlabsgpt-5.6-terraSource: Models.dev data1.1M$1.20cache read $0.12$7.20——
 Routing Rungpt-5.6-terraSource: Models.dev data1M$1.50$9.00——

15 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Human preference

Arena ELO62 related benchmarks · 62 results
Source: LMArena data · Nov 2026
BenchmarkxHigh
Arena ELO
Chinese
Creative Writing
Document
Show 58 more benchmarksHide 58 benchmarks
BenchmarkxHigh
Document Style-Controlled
English
Exclude Ties
Expert
French
German
Hard Prompts
Hard Prompts English
Industry Business and Management and Financial Operations
Industry Entertainment and Sports and Media
Industry Life and Physical and Social Science
Industry Mathematical
Industry Medicine and Healthcare
Industry Software and It Services
Industry Writing and Literature and Language
Japanese
Korean
Longer Query
Multi Turn
Non English
Polish
Russian
Spanish
Style-Controlled
Text Factuality
Text Factuality - Chinese
Text Factuality - Creative Writing
Text Factuality - English
Text Factuality - Exclude Ties
Text Factuality - Expert
Text Factuality - French
Text Factuality - Hard Prompts
Text Factuality - Hard Prompts English
Text Factuality - Industry Business and Management and Financial Operations
Text Factuality - Industry Entertainment and Sports and Media
Text Factuality - Industry Life and Physical and Social Science
Text Factuality - Industry Mathematical
Text Factuality - Industry Medicine and Healthcare
Text Factuality - Industry Software and It Services
Text Factuality - Industry Writing and Literature and Language
Text Factuality - Japanese
Text Factuality - Korean
Text Factuality - Longer Query
Text Factuality - Multi Turn
Text Factuality - Non English
Text Factuality - Polish
Text Factuality - Russian
Text Factuality - Spanish
Vision
Vision - Chinese
Vision - Creative Writing Vision
Vision - Diagram
Vision - English
Vision - Homework
Vision - Humor
Vision Style-Controlled
Design Arena EloSource: Design Arena Leaderboards data · Nov 2026

Coding

Arena ELOSource: LMArena data · Nov 2026
BenchCAD3 results
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Python tool enabled
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
CursorBench 4.0Reasoning effort · Cursor production agent · Reported by Cursor · via BenchBoard docs
ExploitBench2 results
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI GPT-5.6 launch table
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
KernelGen 1P2 results
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI GPT-5.6 launch table
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
NanoGPT2 results
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI GPT-5.6 launch table
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
RSI Index2 results
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI GPT-5.6 launch table
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
SEC-Bench Pro2 results
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI GPT-5.6 launch table
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
ValsSource: Vals AI

Agentic

Arena AgentSource: LMArena data
BrowseComp2 results
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI GPT-5.6 launch table
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Design Arena EloSource: Design Arena Leaderboards data · Nov 2026
GAIA4 results
Source: GAIA Leaderboard data · Sep 2026
Difficulty level
Difficulty not reported
GDPval-AA v23 results
Reported by Z.ai · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Artificial Analysis / Z.ai转载
Reported by Meta · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI GPT-5.6 launch table
OSWorld 2.02 results
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OSWorld 2.0 · OpenAI GPT-5.6 launch table
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI GPT-5.6 launch table
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
SWE-Bench Pro2 results
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI GPT-5.6 launch table
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Source: OpenRouter benchmark exports · Oct 2026
9 Jul 2026 version · 90-day results
Across 3 providers lowest 70.2% median 70.8% highest 71%OpenRouter's automatic routing 72.3%
Show results from 3 providers and OpenRouter's automatic routingHide results from 3 providers and OpenRouter's automatic routing
  • OpenRouter's automatic routing
  • Amazon Bedrock
  • Azure
  • OpenAI
Terminal-Bench 2.13 related benchmarks · 7 results
Terminal-Bench 2.1
Reported by Meta · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI GPT-5.6 launch table
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Terminal-Bench 4.0
Reported by Terminal-Bench / Stanford / Harbor / Laude Institute · via BenchBoard docs
Terminal-Bench 4.0 official leaderboard · Codex · max effort
Source: LLM Stats data
Setting not stated
Reported by SpaceXAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Harbor · provider harness · task success rate · max effort

Reasoning

ARC-AGI3 related benchmarks · 12 results
ARC-AGI
Source: Epoch AI Benchmarking Hub data
Reasoning effort
ARC-AGI 2
Source: Epoch AI Benchmarking Hub data
Reasoning effort
ARC-AGI-3
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI GPT-5.6 launch table
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI GPT-5.6 launch table
Reported by Z.ai · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
v1.0.6 / Z.ai Flash表
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI GPT-5.6 launch table
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
GDP.pdf2 results
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI GPT-5.6 launch table
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
GeneBench Pro2 results
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI GPT-5.6 launch table
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
LifeSciBench2 results
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI GPT-5.6 launch table
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

General

Science

GPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
GPQA Diamond8 results
Source: Epoch AI Benchmarking Hub data
Reasoning effort
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI GPT-5.6 launch table
Source: OpenRouter benchmark exports · Oct 2026
9 Jul 2026 version · 90-day results
Across 3 providers lowest 88.9% median 89.2% highest 89.3%OpenRouter's automatic routing 88.4%
Show results from 3 providers and OpenRouter's automatic routingHide results from 3 providers and OpenRouter's automatic routing
  • Amazon Bedrock
  • Azure
  • OpenAI
  • OpenRouter's automatic routing

Long context

Math

FrontierMath4 related benchmarks · 6 results
FrontierMath
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Tier 1-3 (v2)
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Tier 4 (v2)
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
v2 · GPT-5.6 launch snapshot · 2026-07-09
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Vision

MMMU-Pro3 results
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Multilingual

Instruction following

Factuality

Knowledge

OCR

Other

DeepSWE v1.12 results
Reported by Meta · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI GPT-5.6 launch table
GraphWalks BFSF1 · Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
HealthBench4 related benchmarks · 7 results
HealthBench
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Consensus
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Hard
Source: HealthBench Hard (Arcophos) data docs · Reported by the model's developer. The source relaying it did not verify it. · Jun 2026
length-adjusted, max reasoning effort (34.3 unadjusted, 2,199 mean response chars), GPT-5.6 system card Table 6, column GPT-5.6-TERRA.
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Professional
Reported by OpenAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
OpenAI GPT-5.6 launch table
Source: Clinical Benchmarks data docs · Reported by the model's developer. The source relaying it did not verify it. claim · Jun 2026
Setting not stated
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Horangi36 related benchmarks · 36 results
LatchBio Capabilities v1.011-benchmark live-suite snapshot · equally weighted overall · max effort · Reported by SpaceXAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Nejumi 428 related benchmarks · 28 results
SkillsBench · Vals6 related benchmarks · 6 results
With Skills · Accuracy
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · With Skills · system=openai/gpt-5.6-terra · provider=OpenAI · reasoning_effort=max · max_output_tokens=128000
With Skills · Mean cost / test
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · With Skills · system=openai/gpt-5.6-terra · provider=OpenAI · reasoning_effort=max · max_output_tokens=128000
With Skills · Mean duration / test
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · With Skills · system=openai/gpt-5.6-terra · provider=OpenAI · reasoning_effort=max · max_output_tokens=128000
Without Skills · Accuracy
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · Without Skills · system=openai/gpt-5.6-terra · provider=OpenAI · reasoning_effort=max · max_output_tokens=128000
Without Skills · Mean cost / test
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · Without Skills · system=openai/gpt-5.6-terra · provider=OpenAI · reasoning_effort=max · max_output_tokens=128000
Without Skills · Mean duration / test
Reported by Vals AI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals AI · updated 2026-09-27 · metadata version 1 · 87 tasks in trace charts · 3 trials/task/condition · per-task mean then task average · OpenHands-CLI@ · Without Skills · system=openai/gpt-5.6-terra · provider=OpenAI · reasoning_effort=max · max_output_tokens=128000
SWE-Marathon v1.1native provider harnesses · 8 trials/task · resolution rate · max effort · Reported by SpaceXAI · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Vals14 related benchmarks · 16 results
Show 10 more resultsHide 10 results
MedCode
Source: Clinical Benchmarks data docs · Sep 2026
Setting not stated
Source: Vals AI
Setting not stated
MedScribe
Source: Clinical Benchmarks data docs · Sep 2026
Setting not stated
Source: Vals AI
Setting not stated
MortgageTax
Source: Vals AI

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Data by LLM Stats · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · LMArena, CC BY 4.0 (licence) · Baromètre de l’écriture IA, Johannes Eva; public numeric ranking data, © 2026 Johannes Eva, no results licence stated · BullshitBench by Peter Gostev, MIT (licence) · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence) · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · Keelemudelite mõõdupuu: Independent LLM leaderboard for Estonian. Eesti Keele Instituut. https://moodupuu.eki.ee, CC BY 4.0. Latest per-benchmark results selected with partial-run flags retained. (licence) · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · Arcophos. HealthBench Hard Leaderboard. https://healthbenchhard.ai. CC BY 4.0. Source document linked on each result. (licence) · Horangi 4, Weights & Biases Korea; public publisher-selected numeric evaluation results · LLM Chess by Maxim Saplin, Apache-2.0 (Copyright [2024] [Maxim Saplin]) (licence) · Nejumi Leaderboard 4, Weights & Biases Japan; public publisher-selected numeric evaluation results · Hugging Face official benchmark leaderboards; licence varies by benchmark · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence)

Around the web

Also known as: aihubmix/gpt-5.6-terra, aws-mantle/gpt-5.6-terra, azure/eu/gpt-5.6-terra, azure/gpt-5.6-terra, azure/gpt-5.6-terra-2026-07-09, azure/gpt-5.6-terra@eastus2, azure/gpt-5.6-terra@swedencentral, azure/us-gov/gpt-5.6-terra, azure/us/gpt-5.6-terra, azure_ai/gpt-5.6-terra, azure_ai/gpt-5.6-terra-2026-07-09, bedrock_mantle/openai.gpt-5.6-terra, bedrock_mantle/us-gov-east-1/openai.gpt-5.6-terra, bedrock_mantle/us-gov-west-1/openai.gpt-5.6-terra, chatgpt/gpt-5.6-terra, databricks-gpt-5-6-terra, databricks/databricks-gpt-5-6-terra, github_copilot/gpt-5.6-terra, global.openai.gpt-5.6-terra, gmi/openai/gpt-5.6-terra, gpt-5-6-terra, gpt-5.6 terra, gpt-5.6 terra pro, gpt-5.6-terra-2026-07-09, gpt-5.6-terra-pro, gpt-5.6-terra-xhigh, gpt-5.6-terra-xhigh-codex-harness, gpt-5.6-terra@eu, gpt-56-terra, openai-gpt-5.6-terra, openai-gpt-5.6-terra-pro, openai-gpt-56-terra, openai.gpt-5.6-terra, openai/gpt-5.6-terra, openai/gpt-5.6-terra-batch, openai/gpt-5.6-terra-fast, openai/gpt-5.6-terra-pro, openai/gpt-5.6-terra-pro:batch, openai/gpt-5.6-terra:batch, perplexity/openai/gpt-5.6-terra, replicate/openai/gpt-5.6-terra, us-gov.openai.gpt-5.6-terra, us.openai.gpt-5.6-terra

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works