NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/GPT-6 Luna
OpenAI logo

GPT-6 Luna

by OpenAI · Released Sep 2026

Multimodal1M Context
53.3
avg score
Rank #134
Compare
Better than 59% of all models
Context
1.1M tokens (~525 books)
Input $/1M
$0.10
Output $/1M
$0.50
Type
multimodal
License
Proprietary
Benchmarks
25 tested
Data as of
About

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...

Tested on 25 benchmarks · BenchGecko score 53.3. Top scores: OTIS Mock AIME 2024-2025 (98.9%), GPQA diamond (90.9%), ARC-AGI (86.7%).

Capabilities
coding
34.5
#163 globally
reasoning
73.0
#49 globally
math
79.4
#34 globally
knowledge
35.7
#239 globally
agentic
44.3
#36 globally
speed
51.5
#29 globally
general
44.0
#65 globally
Benchmark Scores
Compare All
Tested on 25 benchmarks · Ranked across 7 categories
Score Distribution (all 326 models)
0255075100
▲ You are here
codingCompare coding →
Frontiercode
42.4·
Mirrorcode
26.7·
reasoningCompare reasoning →
ARC-AGI

Abstraction and Reasoning Corpus. Tests fluid intelligence through novel visual pattern recognition puzzles. Core measure of general intelligence.

86.7·
ARC-AGI-2

ARC-AGI 2, harder sequel to ARC. More complex abstract reasoning patterns that test generalization ability beyond training data.

59.3·
mathCompare math →
OTIS Mock AIME 2024-2025

Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.

98.9·
FrontierMath-Tiers-1-3-v2-Private
83.1·
FrontierMath-Tier-4-v2-Private
56.1·
Quick compare:Alibaba Qwen logovs Qwen3.8 27BGoogle DeepMind logovs Gemma 4 31BAlibaba Qwen logovs Qwen3.5-35B-A3B
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Model Family · OpenAI GPT-6
Sep 2026
93.4
$10.00/M in1.1Mctx34 benchmarks
Sep 2026
$5.00/M in(-5)1.1Mctx
Sep 2026
$10.00/M in(+5)1.1Mctx
Sep 2026
$5.00/M in(-5)1.1Mctx
Sep 2026
53.3-40.1
$0.10/M in(-4.90)1.1Mctx25 benchmarks
Sep 2026
$0.05/M in(-0.05)1.1Mctx
Sep 2026
$0.10/M in(+0.05)1.1Mctx
Sep 2026
$0.05/M in(-0.05)1.1Mctx
Sep 2026
75.4+22.1
$2.00/M in(+1.95)1.1Mctx18 benchmarks
Sep 2026
$1.00/M in(-1)1.1Mctx
Sep 2026
$2.00/M in(+1)1.1Mctx
Sep 2026
$1.00/M in(-1)1.1Mctx
See the full GPT-6 family →
Recently Happened
GPT-6 Luna added
Sep 23, 2026
Similar Models
Alibaba Qwen logo
Qwen3.8 27B
Alibaba Qwen
53.3$0.15/1M
Google DeepMind logo
Gemma 4 31B
Google DeepMind
53.2$0.20/1M
Alibaba Qwen logo
Qwen3.5-35B-A3B
Alibaba Qwen
53.2$0.14/1M
Links
Info
OpenAIPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@OpenAI
BenchGecko API
gpt-6-luna
Specifications
  • Typemultimodal
  • Context1.1M tokens (~525 books)
  • ReleasedSep 2026
  • LicenseProprietary
  • StatusActive
  • Cost / Message~$0.001
Available On
OpenAI logoOpenAI$0.10
Categories
codingreasoningmathknowledgeagenticspeedgeneral
Learn More
context-windowtransformertokens
Share & Export
Tweet
Related Models
Alibaba Qwen logoQwen3.8 27B
53.3
Google DeepMind logoGemma 4 31B
53.2
Alibaba Qwen logoQwen3.5-35B-A3B
53.2
meituan logoLongCat Flash Chat
53.4
GPT-6 Luna is a proprietary multimodal AI model by OpenAI, released in September 2026. It has an average benchmark score of 53.3. Context window: 1M tokens.

Related Models

Qwen3.8 27B · Alibaba QwenGemma 4 31B · Google DeepMindQwen3.5-35B-A3B · Alibaba QwenLongCat Flash Chat · meituanGemini 3 Flash Preview · Google DeepMind

Benchmarks

OTIS Mock AIME 2024-2025GPQA diamondARC-AGIDtbenchArtificial Analysis · Long Context Reasoning

Related Pages

OpenAI · ProviderOpenAI · EconomyAll ModelsCompare ModelsPricingDevelopers · APIContext Window · Glossary

Key facts · as of 2026-11-11

  • GPT-6 Luna by OpenAI. BenchGecko score 53.3, rank 134 of 326 scored models (normalized average of public benchmark scores).
  • List price $0.10 input · $0.50 output per 1M tokens (as of 2026-11-11).
  • Sold by 8 providers (as of 2026-11-11): OpenAI $0.0500 in / $0.25 out · Amazon Bedrock $0.10 in / $0.50 out · Azure $0.10 in / $0.50 out · OpenAI $0.10 in / $0.50 out · Amazon Bedrock $0.11 in / $0.55 out · and 3 more. Every provider
  • Gecko Tests · Gecko Score 61 (rank 10): Who Are You B (Knows who made it) · World Map C (96.2% of the map right) · Censorship Index C (Answers almost everything) · Knowledge Horizon B (Knows news up to Apr 2026) · Tokenizer Tax C (56% more tokens outside English).

How to cite · data as of 2026-11-11

GPT-6 Luna · benchmarks, pricing and providers. BenchGecko, data as of 2026-11-11. https://benchgecko.ai/model/gpt-6-luna

Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP