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

FrontierMath Tiers 1-3 (Epoch AI)‡
41.4% ± 2.92026-08-29low effort, evaluated 2026-08-29
FrontierMath Tiers 1-3 (Epoch AI)‡
82.1% ± 2.32026-07-09max effort, evaluated 2026-07-09
GPQA Diamond (Epoch AI)‡
82.3% ± 2.72026-08-07low effort, evaluated 2026-08-07
GPQA Diamond (Epoch AI)‡
91.6% ± 1.72026-07-09max effort, evaluated 2026-07-09
LiveBench Agentic Coding
48.4%2026-10-18
LiveBench Coding
82.9%2026-10-18
LiveBench Data Analysis
78.0%2026-10-18
LiveBench Instruction Following
60.1%2026-10-18
LiveBench Language
72.6%2026-10-18
LiveBench Math
87.2%2026-10-18
LiveBench Reasoning
85.6%2026-10-18
LMArena Agent‡
-2.22026-10-19xhigh effort
LMArena Agent Bash Recovery‡
0.52026-10-08xhigh effort
LMArena Agent Steerability‡
-1.82026-10-19xhigh effort
LMArena Agent Task Outcome‡
-72026-10-19xhigh effort
LMArena Agent Tool Hallucination‡
0.52026-10-19xhigh effort
LMArena Creative Writing
1396 Elo2026-10-15
LMArena Instruction Following
1437 Elo2026-10-15
LMArena Long Query
1437 Elo2026-10-15
LMArena Math
1459 Elo2026-10-15
LMArena Text
1453 Elo2026-10-15
LMArena Text Factuality
1461 Elo2026-10-15
LMArena Vision‡
1257 Elo2026-10-19xhigh effort
LMArena Vision Diagrams‡
1280 Elo2026-10-19xhigh effort
LMArena Vision OCR‡
1266 Elo2026-10-19xhigh effort
OTIS Mock AIME (Epoch AI)‡
66.7% ± 7.12026-08-07low effort, evaluated 2026-08-07
OTIS Mock AIME (Epoch AI)‡
98.3% ± 1.22026-07-09max effort, evaluated 2026-07-09
SimpleQA Verified (Epoch AI)‡
41% ± 1.62026-08-10max effort, evaluated 2026-08-10
SWE-rebench (2026-05-15 to 2026-07-01)‡
43.6% ± 1.52026-10-20tools, tasks 2026-05-15 to 2026-07-01
Terminal-Bench (4.0)‡
17.3%2026-10-20Codex, max effort, evaluated 2026-08-27

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 4 independent sources. 6 of 6 configured evaluation feeds currently have results.

  • Best LLM for Business WritingEstablished evidence

    100% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Logic & Problem SolvingEstablished evidence

    100% of intended weighted task evidence across 3 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. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Chat & RoleplayEstablished evidence

    100% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Creative WritingEstablished evidence

    100% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

Show all 45 tasks
  • Best LLM for WritingEstablished evidence

    100% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Roleplay & CharacterEstablished evidence

    100% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Math & ReasoningEstablished evidence

    100% of intended weighted task evidence across 5 independent sources. 7 of 7 configured evaluation feeds currently have results.

  • Best LLM for a General AssistantEstablished evidence

    100% of intended weighted task evidence across 3 independent sources. 6 of 6 configured evaluation feeds currently have results.

  • Best LLM for Autonomous AgentsEstablished evidence

    94% of intended weighted task evidence across 4 independent sources. 6 of 6 configured evaluation feeds currently have results.

  • Best LLM for Agentic CodingEstablished evidence

    80% of intended weighted task evidence across 4 independent sources. 7 of 7 configured evaluation feeds currently have results.

  • Best LLM for AI AgentsEstablished evidence

    64% of intended weighted task evidence across 4 independent sources. 9 of 9 configured evaluation feeds currently have results.

  • Best Open-Weight LLM for Self-HostingEstablished evidence

    64% of intended weighted task evidence across 2 independent sources. 2 of 3 configured evaluation feeds currently have results.

  • Best LLM for Image UnderstandingEstablished evidence

    61% of intended weighted task evidence across 2 independent sources. 2 of 3 configured evaluation feeds currently have results.

  • Best LLM for Document SummarizationEstablished evidence

    60% of intended weighted task evidence across 2 independent sources. 5 of 6 configured evaluation feeds currently have results.

  • Best LLM for SummarizationEstablished evidence

    60% of intended weighted task evidence across 2 independent sources. 5 of 6 configured evaluation feeds currently have results.

  • Best LLM for Hermes AgentEstablished evidence

    60% of intended weighted task evidence across 3 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for OpenHandsEstablished evidence

    60% of intended weighted task evidence across 3 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for GooseEstablished evidence

    60% of intended weighted task evidence across 3 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for OpenClawEstablished evidence

    60% of intended weighted task evidence across 3 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Fast SummariesEstablished evidence

    58% of intended weighted task evidence across 2 independent sources. 2 of 3 configured evaluation feeds currently have results.

  • Best Value LLMEstablished evidence

    58% of intended weighted task evidence across 2 independent sources. 2 of 3 configured evaluation feeds currently have results.

  • Best LLM for Debugging & Code ReviewEstablished evidence

    50% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Literary TranslationEstablished evidence

    50% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for Everyday TranslationEstablished evidence

    50% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for TranslationEstablished evidence

    50% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for CodingEstablished evidence

    47% of intended weighted task evidence across 3 independent sources. 7 of 7 configured evaluation feeds currently have results.

  • Best Local LLM for CodingEstablished evidence

    41% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • Best Cheap LLM for High VolumeEstablished evidence

    40% of intended weighted task evidence across 2 independent sources. 2 of 3 configured evaluation feeds currently have results.

  • Cheapest Capable LLMEstablished evidence

    40% of intended weighted task evidence across 2 independent sources. 2 of 3 configured evaluation feeds currently have results.

  • Best LLM for JSON & Schema OutputEstablished evidence

    35% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for Structured Data ExtractionEstablished evidence

    35% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for Grounded RAGEstablished evidence

    29% of intended weighted task evidence across 2 independent sources. 5 of 7 configured evaluation feeds currently have results.

  • Best LLM for OCR & DocumentsProvisional evidence

    65% 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

    65% 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

    60% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 4 of 6 configured evaluation feeds currently have results.

  • Best LLM for Document ParsingProvisional evidence

    58% 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 Massive ContextProvisional evidence

    47% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LongBench v2. 2 of 3 configured evaluation feeds currently have results.

  • Best LLM for Code CompletionProvisional evidence

    43% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Aider Polyglot or LMArena WebDev. 3 of 3 configured evaluation feeds currently have results.

  • Best LLM for RAG & Long ContextProvisional evidence

    39% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LMArena Search. 5 of 6 configured evaluation feeds currently have results.

  • Best LLM for Tool & Function CallingProvisional evidence

    38% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Search. 6 of 7 configured evaluation feeds currently have results.

  • Best LLM for High-Volume ExtractionProvisional evidence

    21% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Route reliability or Structured-output eval. 1 of 3 configured evaluation feeds currently have results.

  • Best LLM for Computer & Browser UseProvisional evidence

    17% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or OSWorld Verified. 3 of 3 configured evaluation feeds currently have results.

  • Best LLM for Frontend & UIProvisional evidence

    9% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Design Arena Coding or Design Arena UI. 6 of 6 configured evaluation feeds currently have results.

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.