GPT-5 High vs GPT-5.6 Luna: Specs & Benchmark Comparison
| Characteristic | GPT-5 High | GPT-5.6 Luna |
|---|---|---|
| Company | OpenAI | OpenAI |
| Release Date | August 6, 2025 | July 9, 2026 |
| Parameters | — | — |
| Multimodal | Yes | Yes |
| Context (input) | 400K | 1.1M |
| Context (output) | 128K | 128K |
| Input Price / 1M | $2.00 | $0.20 |
| Output Price / 1M | $8.00 | $1.20 |
| Average Score | 0.9 | 0.5 |
| Benchmarks | ||
| GPQA | 0.9 | 0.9 |
Visual Benchmark Comparison
GPT-5 High
GPT-5.6 Luna
GPQA0.9 vs 0.9
0.9
0.9
Verdict
GPT-5.6 Luna leads in 3 out of 4 comparison categories.
Overall Performance
Both models show comparable average scores: GPT-5 High — 0.9, GPT-5.6 Luna — 0.5.
API Cost
GPT-5.6 Luna is 7.1x cheaper: input $0.20/1M vs $2.00/1M tokens.
Context Window
GPT-5.6 Luna supports a larger context: 1M vs 400K tokens.
Recency
GPT-5.6 Luna is newer: released 7/9/2026 vs 8/6/2025.
More About These Models
Related Comparisons
Frequently Asked Questions
Which is better for coding — GPT-5 High or GPT-5.6 Luna?
Direct comparison on the SWE-Bench benchmark is not available. We recommend reviewing other metrics on the comparison page.
Which model is cheaper — GPT-5 High or GPT-5.6 Luna?
GPT-5.6 Luna is cheaper for input: $0.20 per 1M tokens vs $2.00.
Which has a larger context window — GPT-5 High or GPT-5.6 Luna?
GPT-5.6 Luna supports a larger context: 1,050,000 tokens vs 400,000.
The GPT-5 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 High or GPT-5.6 Luna page. See also the complete list of AI model comparisons.