GPT-5.6 Luna

openai/gpt-5.6-luna-20260709

OpenAI: GPT-5.6 Luna, released on 2026-07-09, accepts file, image, and text inputs and generates text output. It supports tools and reasoning, has a context length of 1,050,000 tokens, is not open-weight, and is priced at 1 unit per million input tokens and 6 units per million output tokens.

tool use
structured outputs
reasoning

At a glance

provideropenai

releasedJul 9, 2026

context1.1M

input / M$0.20

Specifications

What the API gives you

Context window: 1.1M tokens
Max output: 128K tokens
Input price: $0.20 / 1M tokens
Output price: $1.20 / 1M tokens
Cache read: $0.020 / 1M tokens
Modalities: file, image, text → text
Knowledge cutoff: Feb 16, 2026
Released: Jul 9, 2026

Measured evidence

Public benchmark record

Frontier-Bench^‡: 14.3% ± 1.32026-07-12Codex, max effort
Frontier-Bench^‡: 17.3%2026-06-26Codex, max effort
LiveBench Agentic Coding: 48.4%2026-06-25
LiveBench Coding: 82.9%2026-06-25
LiveBench Data Analysis: 78.0%2026-06-25
LiveBench Instruction Following: 60.1%2026-06-25
LiveBench Language: 72.6%2026-06-25
LiveBench Math: 87.2%2026-06-25
LiveBench Reasoning: 85.6%2026-06-25
LMArena Agent: 3.32026-07-27
LMArena Agent: 3.52026-07-28
LMArena Agent: 4.12026-08-03
LMArena Agent: 4.32026-08-12
LMArena Agent: 4.42026-08-06
LMArena Agent: 4.32026-08-11
LMArena Agent: 4.32026-08-13
LMArena Agent: 3.82026-08-24
LMArena Agent: 3.42026-08-27
LMArena Agent: 2.12026-08-31
LMArena Creative Writing: 1404 Elo2026-07-30
LMArena Creative Writing: 1402 Elo2026-08-02
LMArena Creative Writing: 1402 Elo2026-08-03
LMArena Creative Writing: 1400 Elo2026-08-06
LMArena Creative Writing: 1398 Elo2026-08-12
LMArena Creative Writing: 1393 Elo2026-08-21
LMArena Creative Writing: 1394 Elo2026-08-27
LMArena Creative Writing: 1394 Elo2026-09-01
LMArena Instruction Following: 1442 Elo2026-07-30
LMArena Instruction Following: 1441 Elo2026-08-02
LMArena Instruction Following: 1441 Elo2026-08-03
LMArena Instruction Following: 1436 Elo2026-08-06
LMArena Instruction Following: 1435 Elo2026-08-12
LMArena Instruction Following: 1437 Elo2026-08-21
LMArena Instruction Following: 1437 Elo2026-08-27
LMArena Instruction Following: 1436 Elo2026-09-01
LMArena Long Query: 1440 Elo2026-07-30
LMArena Long Query: 1437 Elo2026-08-02
LMArena Long Query: 1437 Elo2026-08-03
LMArena Long Query: 1433 Elo2026-08-06
LMArena Long Query: 1435 Elo2026-08-12
LMArena Long Query: 1436 Elo2026-08-21
LMArena Long Query: 1436 Elo2026-08-27
LMArena Long Query: 1436 Elo2026-09-01
LMArena Math: 1450 Elo2026-07-30
LMArena Math: 1454 Elo2026-08-02
LMArena Math: 1454 Elo2026-08-03
LMArena Math: 1450 Elo2026-08-06
LMArena Math: 1464 Elo2026-08-12
LMArena Math: 1461 Elo2026-08-21
LMArena Math: 1459 Elo2026-08-27
LMArena Math: 1458 Elo2026-09-01
LMArena Text: 1450 Elo2026-08-02
LMArena Text: 1452 Elo2026-07-30
LMArena Text: 1450 Elo2026-08-03
LMArena Text: 1451 Elo2026-08-10
LMArena Text: 1450 Elo2026-08-06
LMArena Text: 1451 Elo2026-08-21
LMArena Text: 1451 Elo2026-08-12
LMArena Text: 1452 Elo2026-08-27
LMArena Text: 1452 Elo2026-09-01
LMArena Vision: 1248 Elo2026-07-30
LMArena Vision: 1248 Elo2026-08-02
LMArena Vision: 1249 Elo2026-08-06
LMArena Vision: 1253 Elo2026-08-21
LMArena Vision: 1254 Elo2026-08-27
LMArena WebDev: 1525 Elo2026-07-30
LMArena WebDev: 1523 Elo2026-08-01
LMArena WebDev: 1524 Elo2026-07-31
LMArena WebDev: 1523 Elo2026-08-06
LMArena WebDev: 1523 Elo2026-08-02
LMArena WebDev: 1518 Elo2026-08-12
LMArena WebDev: 1519 Elo2026-08-10
LMArena WebDev: 1517 Elo2026-08-14
LMArena WebDev: 1518 Elo2026-08-21
LMArena WebDev: 1518 Elo2026-08-30
LMArena WebDev: 1519 Elo2026-09-01
SWE-rebench^‡: 43.6% ± 1.52026-07-01tools
Terminal-Bench 2.1^‡: 75.7% ± 1.32026-07-11max effort
Terminal-Bench 2.1^‡: 17.3%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 Autonomous AgentsEstablished evidence
95% of intended weighted task evidence across 5 independent sources. 7 of 7 configured evaluation feeds currently have results.
Best LLM for Agentic CodingEstablished evidence
82% of intended weighted task evidence across 5 independent sources. 8 of 8 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 Debugging & Code ReviewEstablished evidence
70% of intended weighted task evidence across 3 independent sources. 6 of 6 configured evaluation feeds currently have results.
Best LLM for CodingEstablished evidence
70% of intended weighted task evidence across 4 independent sources. 8 of 8 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 Local LLM for CodingEstablished evidence
64% of intended weighted task evidence across 3 independent sources. 5 of 5 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 Hermes AgentEstablished evidence
62% of intended weighted task evidence across 3 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for OpenHandsEstablished evidence
62% of intended weighted task evidence across 3 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for GooseEstablished evidence
62% of intended weighted task evidence across 3 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for OpenClawEstablished evidence
62% of intended weighted task evidence across 3 independent sources. 5 of 5 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 AI AgentsProvisional evidence
60% of intended weighted task evidence across 4 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or OSWorld Verified. 7 of 7 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 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 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 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.

Recommendation coverage

Where this model appears

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.