GPT-5.1 High vs GPT-5.6 Luna: Specs & Benchmark Comparison
GPT-5.1 High and GPT-5.6 Luna both come from OpenAI, GPT-5.1 High was released in November 2025, and GPT-5.6 Luna followed 8 months later in July 2026.
We have 3 benchmark results for GPT-5.1 High and 45 benchmark results for GPT-5.6 Luna, but they overlap on a single test: GPQA, where GPT-5.6 Luna scores 92.3% against 88.0%.
GPT-5.6 Luna is the cheaper API at $0.20 per million input tokens and $1.20 per million output tokens, roughly 6 times cheaper than GPT-5.1 High at $1.25 and $10. GPT-5.6 Luna takes the larger context window at 1M tokens, compared with 400K for GPT-5.1 High. Both accept text and images as input.
| Characteristic | GPT-5.1 High | GPT-5.6 Luna |
|---|---|---|
| Company | OpenAI | OpenAI |
| Release Date | November 11, 2025 | July 9, 2026 |
| Parameters | — | — |
| Multimodal | Yes | Yes |
| Context (input) | 400K | 1.1M |
| Context (output) | 128K | 128K |
| Input Price / 1M | $1.25 | $0.20 |
| Output Price / 1M | $10.00 | $1.20 |
| Average Score | 86.7% | 51.5% |
| Benchmarks | ||
| GPQA | 88.0% | 92.3% |
Visual Benchmark Comparison
Verdict
GPT-5.6 Luna leads in 3 out of 4 comparison categories.
Both models show comparable average scores: GPT-5.1 High — 0.9, GPT-5.6 Luna — 0.5.
GPT-5.6 Luna is 8.0x cheaper: input $0.20/1M vs $1.25/1M tokens.
GPT-5.6 Luna supports a larger context: 1M vs 400K tokens.
GPT-5.6 Luna is newer: released 7/9/2026 vs 11/11/2025.
More About These Models
Frequently Asked Questions
Which is better for coding — GPT-5.1 High or GPT-5.6 Luna?
Which model is cheaper — GPT-5.1 High or GPT-5.6 Luna?
Which has a larger context window — GPT-5.1 High or GPT-5.6 Luna?
The GPT-5.1 High and GPT-5.6 Luna comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the GPT-5.1 High or GPT-5.6 Luna page. See also the complete list of AI model comparisons.