GPT-5.6 Luna
OpenAI · 6 thinking configurations
Intelligence32.1
Input / 1M$0.20
Output / 1M$1.20
Context1M
Tariff: OpenAI · Source: artificial-analysis · USD per million tokens
Thinking configuration
What does more thinking buy you?
Compare this model’s measured thinking configurations.
Scroll the chart ↔ · tap a point for details
Efficient frontier: best measured score at each cost6 measured configurations · 0 without both values
Selected: thinking high · Click a point to switch configuration
GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
32.1 pointsDeepSWE · pass@1Software-engineering tasks on mini-swe-agent v1.1. Pass@1 across evaluated runs, with measured cost per task. The 95% intervals may overlap.
44.2 % ±2.9GPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
89.2 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
33.4 %SciCodeCode generation for scientific research problems.
51.6 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
69.7 %MMMU-ProMultimodal understanding of academic problems that include images.
77.6 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
41.8 %Specifications from the catalog
Inputfile, image, text
Outputtext
Tool callingYes
Structured outputYes
Speed105.8 tok/s
First token14.41 s
Maximum output128K
Catalog listing date2026-07-09
DeepSWE v1.1 · 113 tasks · mini-swe-agent · cost $0.78 / task · 49 mean steps · 25.8K mean output tokens. Published by the source 9/22/2026.