GPT-5.6 Luna vs GPT-5.6 Sol
GPT-5.6 Luna (OpenAI) and GPT-5.6 Sol (OpenAI) compared on benchmarks, pricing, context window, and use-case rankings.
- GPT-5.6 Sol leads on overall intelligence (ECI 161 vs 156).
- GPT-5.6 Luna is cheaper on input tokens — $0.20 vs $5.00 per 1M.
- GPT-5.6 Sol ranks higher for coding (94th vs 76th percentile).
| Attribute | GPT-5.6 Luna | GPT-5.6 Sol |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 156 | 161 |
| Coding | 76 | 94 |
| Math | 87 | 97 |
| Reasoning & Knowledge | 57 | 94 |
| Agentic & Tools | — | 64 |
| Specifications | ||
| Developer | OpenAI | OpenAI |
| Family | GPT | GPT |
| Released | Jul 9, 2026 | Jul 9, 2026 |
| Parameters | — | — |
| Availability | API access | API access |
| Context window | 1.1M | 1.1M |
| Price — $/M input | $0.20 | $5.00 |
| Price — $/M output | $1.20 | $30.00 |
| Inputs | file, image, text | file, image, text |
| Outputs | text | text |
| Benchmarks | ||
| AIME 2024/2025 | 98% | 100% |
| ARC-AGI | 88% | 98% |
| ARC-AGI-2 | 60% | 93% |
| GPQA Diamond | 92% | 93% |
| Humanity's Last Exam | 40% | 50% |
| SciCode | 53% | 56% |
| SimpleBench | 47% | 72% |
| SimpleQA Verified | 42% | 72% |
| WebDev Arena | 1523 | 1620 |
| WeirdML | 61% | 89% |
| APEX | — | 40% |
| τ²-bench | — | 85% |
Use-case scores are 0–100 percentile composites across each area’s benchmarks, ranked against every model from the past year. Highlighted cells lead each row. Open a model for the full picture.
Frequently asked questions
Is GPT-5.6 Luna better than GPT-5.6 Sol?
On Epoch AI's Capabilities Index, GPT-5.6 Sol scores higher (161) than GPT-5.6 Luna (156). The right pick depends on your task — compare their coding, math, and reasoning scores in the table above.
Which is cheaper, GPT-5.6 Luna or GPT-5.6 Sol?
GPT-5.6 Luna is cheaper on input tokens at $0.20 per million, versus $5.00 (representative OpenRouter pricing).
Which has a larger context window, GPT-5.6 Luna or GPT-5.6 Sol?
GPT-5.6 Luna supports up to 1.1M tokens, compared with 1.1M for the other.
Which is better for coding, GPT-5.6 Luna or GPT-5.6 Sol?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, GPT-5.6 Sol ranks higher — 94th vs 76th percentile among the models tracked on Model Beat.
Want a different match-up? Open the compare tool to add or swap models.
More comparisons
Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.