DataLearner logo
GP

GPT-5.6 Luna

Reasoning modelGPT-5.6

GPT-5.6 Luna

Release date: 2026-06-26Updated: 2026-07-12 10:13:25.871Knowledge cutoff: 2026-02-16515
Live demoGitHubHugging FaceCompare
Parameters
Not disclosed
Context length
1.05M
Chinese support
Supported
Reasoning ability

GPT-5.6 Luna is an AI model from OpenAI, released on 2026-06-26.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

GPT-5.6 Luna

Model basics

Reasoning traces
Supported
Thinking modes
Thinking Level · Medium (Default)Standard ModeThinking Level · LowThinking Level · High
Context length
1.05M tokens
Max output length
128K tokens
Model type
Reasoning model
Modality (in / out)
Text, Image → Text
Release date
2026-06-26
Model file size
No data
MoE architecture
No
Total params / Active params
No data / N/A
Knowledge cutoff
2026-02-16
GPT-5.6 Luna

Open source & experience

Code license
Proprietary
Weights license
Proprietary
GitHub repo
GitHub link unavailable
Hugging Face
Hugging Face link unavailable
Live demo
No live demo
GPT-5.6 Luna

Official resources

DataLearnerAI blog
No blog post yet
GPT-5.6 Luna

API details

API speed
5/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
TypeConditionInputOutput
Text-$1.00/ 1M$6.00/ 1M
long-context
TypeConditionInputOutput
Textcontext_tokens > 272000$2.00/ 1M$9.00/ 1M
Cache PricingPrompt Cache
TypeTTLWriteRead
Text30m$1.25/ 1M$0.100/ 1M
GPT-5.6 Luna

Benchmark Results

GPT-5.6 Luna currently shows benchmark results led by TerminalBench 2.1 (6 / 29, score 84.70), ARC-AGI (19 / 68, score 88), DeepSWE (6 / 20, score 67.20). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking
Tool usage

General Knowledge

4 evaluations
Benchmark / mode
Score
Rank/total
88
19 / 68
59.50
20 / 62
0.20
3 / 9

AI Agent - Tool Usage

1 evaluations
Benchmark / mode
Score
Rank/total
84.70
6 / 29

Coding and Software Engineer

2 evaluations
Benchmark / mode
Score
Rank/total
AA Coding Agent Index
Extra-HighTools
74.60
3 / 3
DeepSWE
Extra-HighTools
67.20
6 / 20

Agent Level Benchmark

1 evaluations
Benchmark / mode
Score
Rank/total
Agents' Last Exam
Extra-HighTools
50.30
3 / 5

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

GPT-5.6 Luna

Publisher

GPT-5.6 Luna

Model Overview

GPT-5.6 Luna

GPT-5.6 Luna is OpenAI's most cost-efficient tier in the GPT-5.6 family, first previewed on June 26, 2026 and made generally available on July 9, 2026. It's built for high-throughput, cost-sensitive tasks — summarization, drafting, routine automation — and is the fastest and cheapest of the three GPT-5.6 models. The family also includes Sol (the flagship) and Terra (the balanced mid-tier).

On Artificial Analysis's Intelligence Index (max reasoning), Luna scores 51 at roughly one-fifth Sol's cost per task (~$0.21 vs ~$1.04), delivering about 24 benchmark points per estimated API dollar. It reaches 84.70 on Terminal-Bench 2.1, 67.20 on DeepSWE, 74.6 on the AA Coding Agent Index, and 50.3 on Agents' Last Exam. Long-context recall is comparatively weak (41.3% on MRCR), so it's best reserved for shorter, well-scoped jobs rather than large-document workflows.

Luna shares OpenAI's GPT-5.6 system card with Sol and Terra, including "High" Preparedness Framework ratings for cybersecurity and biological/chemical risk; see the GPT-5.6 Sol page for the detailed safety-evaluation breakdown.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code