Skip to main content

GPT-5.6 Luna

OpenAIGPTProprietary

Description

GPT-5.6 Luna is the fastest and most cost-efficient tier of OpenAI's GPT-5.6 family, designed for cost-sensitive, high-volume workloads. It brings strong capability at OpenAI's lowest GPT-5.6 price, supports max reasoning effort, and has a 1.05M-token context window.

Release Date
2026-07-09
Parameters
Context Length
1.1M
Modalities
image, pdf, text

Capability Radar

100
general
6
coding
60
reasoning
77
scienceest.
70
agents
70
multimodal

Science uses a reasoning proxy when dedicated science benchmarks are unavailable.

Rankings

Domain#RankScoreSource
Agentic Capability98
48.0
LS

Benchmark Scores (LLM Stats)

Agents

GDPval-AA1591.80 / 3000SR
Artificial Analysis Coding Agent Index v1.174.60 / 100SR
Connectors99.9%SR
Search and Function-Calling89.7%SR
Capture-the-Flag Challenges (Internal)85.2%SR
Terminal-Bench 2.184.7%SR
BrowseComp83.3%SR
DeepSWE67.2%SR
SWE-Bench Pro62.7%SR
Toolathlon53.4%SR
LifeSciBench51.2%SR
Internal Research Debugging Evaluation50.8%SR
Agents' Last Exam50.3%SR
SEC-bench Pro48.9%SR
OSWorld 2.045.6%SR
RSI Index41.9%SR
Big Finance Bench36.0%SR
Management Consulting Tasks (Internal)35.4%SR
ExploitBench33.2%SR
PostTrainBench Lite29.6%SR
KernelGen 1P22.4%SR
AutomationBench14.9%SR
ExploitGym12.4%SR
GeneBench-Pro10.8%SR
NanoGPT1.7%SR

Biology

GPQA92.3%SR

Code

BenchCAD73.9%SR

General

MMMU-Pro79.5%SR
Artificial Analysis51.0%SR
MRCR v2 (8-needle)41.3%SR
GDP.pdf22.7%SR
ARC-AGI-30.2%SR

Healthcare

HealthBench Consensus95.1%SR
HealthBench55.8%SR
HealthBench Professional55.7%SR
HealthBench Hard32.0%SR
MedChemBench (Internal)30.4%SR

Long Context

Graphwalks BFS >128k51.2%SR

Math

FrontierMath58.5%SR

AA Evaluation Indices

No AA evaluation data available

LLM Stats Category Scores

Legal
100
Finance
100
General
100
Reasoning
70
Agents
67
Code
6
Physics
90
Biology
90
Chemistry
90
Search
80
Tool Calling
70
Math
60
Multimodal
60
Vision
60
Spatial Reasoning
50
Long Context
50
Healthcare
50
Safety
40
Science
30
Systems
20

Pricing

Input Price$0 / 1M tokens
Output Price$0.00001 / 1M tokens
Blended Price (3:1)$0 / 1M tokens
Cache Read Price$0.1 / 1M tokens
Cache Write Price$1.25 / 1M tokens

Speed

No speed data available

Provider Price Ranking

Provider Price Ranking

8 providers

Cheapest: OpenAIMost Expensive: AI-ROUTER
ProviderInputOutput
1OpenAIPRIMARY
$0
$0.00001
2routing.run
$0.7
$4.2
3Abacus
$1
$6
4Vivgrid
$1
$6
5GitHub Copilot
$1
$6
6OpenCode Zen
$1
$6
7LLM Gateway
$1
$6
8AI-ROUTER
$1
$6

Compare pricing across different API providers for this model.

External Sources

GPT-5.6 Luna — OpenAI | AITier