GPT-6 Luna
OpenAI · released Sep 22, 2026
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...
Specification
- Context window
- 1.05M
- Max output
- 128K
- Knowledge cutoff
- Not stated
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 3
- Moderated
- Yes
- Uptime
- 100.0%
Intelligence
38.1
89th percentile
Coding
—
Coding Index
Agentic
—
Agentic Index
Output speed
98 t/s
Median across providers
Latency
1.07s
Time to first token
Cost per task
$0.04
Estimated
Benchmarks
Where the score comes from
The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.
Evaluation scores
Percentage correct · higher is better
- AA-LCR (long context)83.3%
- SciCode54.6%
- Humanity's Last Exam38.5%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| AA-LCR (long context) | 83.3% |
| SciCode | 54.6% |
| Humanity's Last Exam | 38.5% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- Gemini 3.7 FlashGoogle39.1
- GPT-5.4OpenAI39.0
- Grok 4.5xAI38.8
- GPT-5.5OpenAI38.4
- Claude Sonnet 5Anthropic38.2
- GPT-6 LunaOpenAI38.1
- MiMo-V2.6-FlashXiaomi37.9
- GPT-5.6 LunaOpenAI37.3
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Gemini 3.7 Flash | 39.1 |
| GPT-5.4 | 39.0 |
| Grok 4.5 | 38.8 |
| GPT-5.5 | 38.4 |
| Claude Sonnet 5 | 38.2 |
| GPT-6 Luna | 38.1 |
| MiMo-V2.6-Flash | 37.9 |
| GPT-5.6 Luna | 37.3 |
Percentile among all indexed models
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- $0.1
- Output / 1M tokens
- $0.5
- Cached input / 1M
- $0.01
- Blended 3:1
- $0.2
One task, estimated
$0.04
- Input tokens
- 50,000
- Output tokens
- 80,000
- Profile
- Reasoning
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).
Serving providers
Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.
Arena
Head-to-head generation quality
Elo from pairwise judgements, broken out by the kind of thing the model was asked to build.
- Overall Elo
- 1,303
- Win rate
- 53.2%
- Strongest at
- UI components
- Tournaments
- 1,394
Elo by category
Dot position on a 1,150–1,325 scale · Elo has no meaningful zero
- 1,303
- 1,274
- 1,260
- 1,248
- 1,219
- 1,213
- 1,158
Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.
View as table
| Category | Elo | Win rate |
|---|---|---|
| UI components | 1303 | 53.2% |
| Websites | 1274 | 47.8% |
| Game development | 1260 | 46.8% |
| SVG | 1248 | 47.2% |
| 3D scenes | 1219 | 42.4% |
| Data visualisation | 1213 | 43.6% |
| Full-stack apps | 1158 | 39.9% |