GPT-5.6 Terra
openai/gpt-5.6-terra-20260709
OpenAI's GPT-5.6 Terra, released on 2026-07-09, processes file, image, and text inputs and generates text output. It supports tool usage and reasoning, provides a context length of 1,050,000 tokens, and is priced at $2.5 per million input tokens and $15 per million output tokens. The model’s weights are not open.
- tool use
- structured outputs
- reasoning
At a glance
Specifications
What the API gives you
- Context window
- 1.1M tokens
- Max output
- 128K tokens
- Input price
- $2 / 1M tokens
- Output price
- $12 / 1M tokens
- Cache read
- $0.20 / 1M tokens
- Modalities
- file, image, text → text
- Knowledge cutoff
- Feb 16, 2026
- Released
- Jul 9, 2026
Measured evidence
Public benchmark record
- Frontier-Bench‡
- 20.8% ± 1.42026-07-12Codex, max effort
- Frontier-Bench‡
- 21.5%2026-06-26Codex, max effort
- LiveBench Agentic Coding
- 55.0%2026-06-25
- LiveBench Coding
- 78.3%2026-06-25
- LiveBench Data Analysis
- 79.3%2026-06-25
- LiveBench Instruction Following
- 64.6%2026-06-25
- LiveBench Language
- 82.9%2026-06-25
- LiveBench Math
- 94.9%2026-06-25
- LiveBench Reasoning
- 90.6%2026-06-25
- LMArena Agent
- 42026-07-27
- LMArena Agent
- 3.52026-07-28
- LMArena Agent
- 3.52026-08-03
- LMArena Agent
- 3.72026-08-12
- LMArena Agent
- 3.12026-08-06
- LMArena Agent
- 3.42026-08-11
- LMArena Agent
- 3.82026-08-13
- LMArena Agent
- 3.32026-08-24
- LMArena Agent
- 2.92026-08-31
- LMArena Agent
- 32026-09-05
- LMArena Agent
- 32026-08-27
- LMArena Creative Writing
- 1411 Elo2026-07-30
- LMArena Creative Writing
- 1400 Elo2026-08-02
- LMArena Creative Writing
- 1400 Elo2026-08-03
- LMArena Creative Writing
- 1405 Elo2026-08-06
- LMArena Creative Writing
- 1409 Elo2026-08-12
- LMArena Creative Writing
- 1405 Elo2026-08-21
- LMArena Creative Writing
- 1409 Elo2026-09-02
- LMArena Creative Writing
- 1406 Elo2026-08-27
- LMArena Creative Writing
- 1409 Elo2026-09-01
- LMArena Instruction Following
- 1454 Elo2026-07-30
- LMArena Instruction Following
- 1454 Elo2026-08-02
- LMArena Instruction Following
- 1454 Elo2026-08-03
- LMArena Instruction Following
- 1456 Elo2026-08-06
- LMArena Instruction Following
- 1453 Elo2026-08-12
- LMArena Instruction Following
- 1452 Elo2026-08-21
- LMArena Instruction Following
- 1454 Elo2026-09-02
- LMArena Instruction Following
- 1454 Elo2026-08-27
- LMArena Instruction Following
- 1454 Elo2026-09-01
- LMArena Long Query
- 1454 Elo2026-07-30
- LMArena Long Query
- 1454 Elo2026-08-02
- LMArena Long Query
- 1454 Elo2026-08-03
- LMArena Long Query
- 1453 Elo2026-08-06
- LMArena Long Query
- 1451 Elo2026-08-12
- LMArena Long Query
- 1453 Elo2026-08-21
- LMArena Long Query
- 1454 Elo2026-09-02
- LMArena Long Query
- 1453 Elo2026-08-27
- LMArena Long Query
- 1454 Elo2026-09-01
- LMArena Math
- 1473 Elo2026-07-30
- LMArena Math
- 1460 Elo2026-08-02
- LMArena Math
- 1460 Elo2026-08-03
- LMArena Math
- 1465 Elo2026-08-06
- LMArena Math
- 1467 Elo2026-08-12
- LMArena Math
- 1465 Elo2026-08-21
- LMArena Math
- 1466 Elo2026-09-01
- LMArena Math
- 1469 Elo2026-08-27
- LMArena Text
- 1468 Elo2026-07-30
- LMArena Text
- 1468 Elo2026-08-02
- LMArena Text
- 1467 Elo2026-08-06
- LMArena Text
- 1468 Elo2026-08-03
- LMArena Text
- 1465 Elo2026-08-10
- LMArena Text
- 1465 Elo2026-08-21
- LMArena Text
- 1465 Elo2026-08-12
- LMArena Text
- 1466 Elo2026-09-01
- LMArena Text
- 1466 Elo2026-09-02
- LMArena Text
- 1466 Elo2026-08-27
- LMArena Vision
- 1273 Elo2026-07-30
- LMArena Vision
- 1269 Elo2026-08-02
- LMArena Vision
- 1270 Elo2026-08-06
- LMArena Vision
- 1266 Elo2026-08-21
- LMArena Vision
- 1266 Elo2026-08-27
- LMArena WebDev
- 1522 Elo2026-07-30
- LMArena WebDev
- 1522 Elo2026-08-01
- LMArena WebDev
- 1521 Elo2026-07-31
- LMArena WebDev
- 1526 Elo2026-08-06
- LMArena WebDev
- 1522 Elo2026-08-02
- LMArena WebDev
- 1523 Elo2026-08-12
- LMArena WebDev
- 1524 Elo2026-08-10
- LMArena WebDev
- 1521 Elo2026-08-14
- LMArena WebDev
- 1518 Elo2026-09-01
- LMArena WebDev
- 1520 Elo2026-09-05
- LMArena WebDev
- 1520 Elo2026-08-21
- LMArena WebDev
- 1519 Elo2026-08-30
- Terminal-Bench 2.1‡
- 78.4% ± 1.32026-07-11max effort
- Terminal-Bench 2.1‡
- 21.5%2026-06-26max effort
LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Design Arena uses blind human preference. ‡ Submitted scaffold plus model result. Compare the harness and effort settings, not only the model name.
Task evidence
How broad is the support?
Each status is exact to this model version and the selected task. Official release claims remain provisional.
- Best LLM for Competition MathEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Business WritingEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Logic & Problem SolvingEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Marketing CopyEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Chat & RoleplayEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Creative WritingEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for WritingEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Roleplay & CharacterEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Math & ReasoningEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for a General AssistantEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for Code CompletionEstablished evidence
81% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.
- Best LLM for Autonomous AgentsEstablished evidence
71% of intended weighted task evidence across 4 independent sources. 7 of 7 configured evaluation feeds currently have results.
- Best Open-Weight LLM for Self-HostingEstablished evidence
67% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.
- Best LLM for Image UnderstandingEstablished evidence
65% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.
- Best LLM for Fast SummariesEstablished evidence
64% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.
- Best Value LLMEstablished evidence
64% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.
- Best LLM for Agentic CodingEstablished evidence
64% of intended weighted task evidence across 4 independent sources. 8 of 8 configured evaluation feeds currently have results.
- Best LLM for Document SummarizationEstablished evidence
60% of intended weighted task evidence across 2 independent sources. 4 of 6 configured evaluation feeds currently have results.
- Best LLM for SummarizationEstablished evidence
60% of intended weighted task evidence across 2 independent sources. 4 of 6 configured evaluation feeds currently have results.
- Best LLM for Literary TranslationProvisional evidence
55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from WMT translation. 4 of 5 configured evaluation feeds currently have results.
- Best LLM for Everyday TranslationProvisional evidence
55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from WMT translation. 4 of 5 configured evaluation feeds currently have results.
- Best LLM for TranslationProvisional evidence
55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from WMT translation. 4 of 5 configured evaluation feeds currently have results.
- Best LLM for CodingProvisional evidence
54% of intended weighted task evidence across 3 independent sources; broader independent confirmation is still missing from Aider Polyglot or Design Arena Coding. 8 of 8 configured evaluation feeds currently have results.
- Best LLM for Hermes AgentProvisional evidence
51% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or SWE-rebench. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for OpenHandsProvisional evidence
51% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or SWE-rebench. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for GooseProvisional evidence
51% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or SWE-rebench. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for OpenClawProvisional evidence
51% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or SWE-rebench. 5 of 5 configured evaluation feeds currently have results.
- Best Cheap LLM for High VolumeProvisional evidence
50% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Route reliability. 3 of 4 configured evaluation feeds currently have results.
- Cheapest Capable LLMProvisional evidence
50% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Route reliability. 3 of 4 configured evaluation feeds currently have results.
- Best LLM for Massive ContextProvisional evidence
50% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LongBench v2. 3 of 4 configured evaluation feeds currently have results.
- Best Local LLM for CodingProvisional evidence
50% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Aider Polyglot or SWE-rebench. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for OCR & DocumentsProvisional evidence
45% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 3 of 5 configured evaluation feeds currently have results.
- Best LLM for Vision & DocumentsProvisional evidence
45% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 3 of 5 configured evaluation feeds currently have results.
- Best LLM for Charts & DiagramsProvisional evidence
45% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 3 of 5 configured evaluation feeds currently have results.
- Best LLM for Document ParsingProvisional evidence
45% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 3 of 5 configured evaluation feeds currently have results.
- Best LLM for AI AgentsProvisional evidence
45% of intended weighted task evidence across 3 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or OSWorld Verified. 7 of 7 configured evaluation feeds currently have results. Official release evidence is also tracked provisionally.
- Best LLM for Debugging & Code ReviewProvisional evidence
40% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Aider Polyglot or SWE-bench Verified. 6 of 6 configured evaluation feeds currently have results.
- Best LLM for Frontend & UIProvisional evidence
40% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Design Arena Coding or Design Arena UI. 5 of 5 configured evaluation feeds currently have results.
- Best LLM for JSON & Schema OutputProvisional evidence
39% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or Structured-output eval. 4 of 5 configured evaluation feeds currently have results.
- Best LLM for Structured Data ExtractionProvisional evidence
39% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or Structured-output eval. 4 of 5 configured evaluation feeds currently have results.
- Best LLM for RAG & Long ContextProvisional evidence
35% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LMArena Search. 4 of 6 configured evaluation feeds currently have results.
- Best LLM for High-Volume ExtractionProvisional evidence
31% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Route reliability or Structured-output eval. 2 of 4 configured evaluation feeds currently have results.
- Best LLM for Tool & Function CallingProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Search. 4 of 5 configured evaluation feeds currently have results.
- Best LLM for Computer & Browser UseProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or OSWorld Verified. 4 of 4 configured evaluation feeds currently have results.
- Best LLM for Grounded RAGProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from CRAG or FACTS Grounding. 2 of 5 configured evaluation feeds currently have results.
Official release evidence · provisional
What the launch material actually says
Verbatim claims from the model provider. These help on launch day but do not count as independent confirmation.
“Terra performs just above Fable 5, while Luna outperforms Opus 4.8; each does so in roughly one-third of the time, with about half as many output tokens, and at approximately one-quarter the estimated cost.”
OpenAI · GPT-5.6: Frontier intelligence that scales with your ambition | OpenAI“GPT‑5.6 Terra and GPT‑5.6 Luna outperform Fable 5 at around one-sixteenth the cost.”
OpenAI · GPT-5.6: Frontier intelligence that scales with your ambition | OpenAI
Recommendation coverage
Where this model appears
Not currently included in a published recommendation. The task evidence panel above says exactly what is confirmed and what is still missing.
Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.