Hardest reasoning tasks
Choose GPT-5.6 Luna
GPT-5.6 Luna scores 37.3 on the Artificial Analysis Intelligence Index, against 33.7 for Muse Spark 1.1.
GPT-5.6 Luna vs Muse Spark 1.1: price, context and capabilities
Choose GPT-5.6 Luna for the hardest reasoning tasks and reasoning over long documents; on the other points the two are level or the data is missing.
In short
- A price comparison is not possible: one of them has no comparable published price.
- GPT-5.6 Luna reads more per request: 1.05M tokens against 1.05M.
- Only GPT-5.6 Luna offers reasoning, structured output, prompt caching, batch api.
Which should you choose?
Each answer below comes straight from the published prices, specifications and independent benchmark results.
Reasoning over long documents
Choose GPT-5.6 Luna
GPT-5.6 Luna scores 83.7% on Long-context reasoning (AA-LCR), against 77.7% for Muse Spark 1.1.
Specifications side by side
| GPT-5.6 Luna | Muse Spark 1.1 | |
|---|---|---|
| Provider | OpenAI | Meta |
| Category | Language models | Language models |
| Status | Generally available | Legacy |
| Headline price | $0.45 / 1M tokens | No data |
| Input | $0.20 / 1M tokens | No data |
| Output | $1.20 / 1M tokens | No data |
| Cached input | $0.02 / 1M tokens | No data |
| Context window | 1.05M | 1.05M |
| Max output | 128k | No data |
| Released | Jul 9, 2026 | Jul 9, 2026 |
| Knowledge cutoff | February 2026 | No data |
| Licence | Proprietary | Proprietary |
| Capabilities | Vision, Reasoning, Tool calling, Structured output, Prompt caching, Batch API | Vision, Tool calling |
| API model id | gpt-5.6-luna | muse-spark-1.1 |
Benchmarks side by side
Leader in bold.
| Benchmark | GPT-5.6 Luna | Muse Spark 1.1 |
|---|---|---|
| Intelligence Index | 37.3 | 33.7 |
| SciCode | 53.6% | 58.8% |
| GPQA Diamond | 91.1% | 89.8% |
| Humanity's Last Exam | 39.5% | 46.2% |
| Long-context reasoning (AA-LCR) | 83.7% | 77.7% |
| MMMU-Pro (visual reasoning) | 78.6% | No data |
Independent evaluations by Artificial Analysis, run the same way for every model, at the reasoning setting shown. Percentages unless marked as an index.
Frequently asked questions
Should I choose GPT-5.6 Luna or Muse Spark 1.1?
Choose GPT-5.6 Luna for the hardest reasoning tasks and reasoning over long documents; on the other points the two are level or the data is missing.
Which is cheaper, GPT-5.6 Luna or Muse Spark 1.1?
A price comparison is not possible: one of them has no comparable published price.
Which has the larger context window, GPT-5.6 Luna or Muse Spark 1.1?
GPT-5.6 Luna reads more per request: 1.05M tokens against 1.05M.
What is the difference between GPT-5.6 Luna and Muse Spark 1.1?
GPT-5.6 Luna is made by OpenAI and Muse Spark 1.1 by Meta. A price comparison is not possible: one of them has no comparable published price. GPT-5.6 Luna reads more per request: 1.05M tokens against 1.05M. Only GPT-5.6 Luna offers reasoning, structured output, prompt caching, batch api.