GPT-5.5 Pro vs GPT-5.6 Luna
GPT-5.5 Pro Verdict
- GPT-5.5 Pro (xhigh) leads on quality: 67.1 vs 61.1.
- GPT-5.5 Pro (xhigh) is stronger in maths, reasoning.
- GPT-5.6 Luna (xhigh) is stronger in agents & tools, coding, composite, human preference, knowledge, long context, multimodal.
- GPT-5.6 Luna (xhigh) is 150× cheaper ($0.450 vs $67.50 per 1M blended).
- GPT-5.6 Luna (xhigh) streams 31.0× faster (124 vs 4 tokens per second).
| Metric | GPT-5.5 Pro (xhigh) | GPT-5.6 Luna (xhigh) |
|---|---|---|
| BenchLeader Index | 67.1 | 61.1 |
| Maths score | 74.5 | 67.0 |
| Reasoning score | 80.1 | 60.1 |
| Agents & tools score | – | 54.1 |
| Coding score | – | 59.8 |
| Composite score | – | 73.1 |
| Human preference score | – | 64.8 |
| Knowledge score | – | 59.1 |
| Long context score | – | 67.3 |
| Multimodal score | – | 61.6 |
| Blended price $/M | $67.50 | $0.450 |
| Output speed | 4 tok/s | 124 tok/s |
| Time to first answer | 3.5 s | 34.9 s |
| Context window | 1.1M | 1.1M |
| FrontierMath Tiers 1–3 | 87.7% | – |
| FrontierMath Tier 4 | 78.0% | – |
| SimpleBench | – | 46.8% |
| SciCode | – | 50.0% |
| LMArena Text | – | 1453 |
| LMArena Hard Prompts | – | 1473 |
| LMArena Coding | – | 1498 |
| LMArena WebDev | – | 1519 |
| LMArena Vision | – | 1259 |
| LMArena Agent | – | -0.4 |
| AA Intelligence Index | – | 34.8 |
| AA-LCR | – | 81.7% |
| MMMU-Pro | – | 78.5% |
| AA-Omniscience | – | -10.8 |
| GPQA Diamond (AA) | – | 89.5% |
| Humanity's Last Exam (AA) | – | 37.0% |
| SciCode (AA) | – | 50.5% |
| ARC-AGI-1 | 95.0% | 87.7% |
| ARC-AGI-2 | 84.2% | 47.6% |
| ARC-AGI-3 | – | 0.0% |
| CritPt | 30.6% | 20.6% |
| GDPval (AA) | – | 46.4% |
| τ²-Bench Banking (AA) | – | 28.7% |
| LMArena Maths | – | 1477 |
| LMArena Creative Writing | – | 1411 |
| LMArena Instruction Following | – | 1442 |
| LMArena Multi-turn | – | 1458 |
| LMArena Longer Queries | – | 1450 |
| LMArena Document | – | 1462 |
| DeepSWE | – | 56.9% |
| LMCA | 53.9% | – |
| DTBench | 96.0% | – |
| CursorBench | – | 57.7% |
Data as of 2026-09-19. Best configuration of each model; every score links to its source on the model pages.
GPT-5.5 Pro vs GPT-5.6 Luna: questions
- Is GPT-5.5 Pro better than GPT-5.6 Luna?
- GPT-5.5 Pro (xhigh) leads on quality: 67.1 vs 61.1. The BenchLeader Index combines every independent quality benchmark; GPT-5.5 Pro (xhigh) is ahead overall as of 2026-09-19, but check the category scores for your use.
- Which is cheaper, GPT-5.5 Pro or GPT-5.6 Luna?
- GPT-5.6 Luna is cheaper: $0.450 against $67.50 per million tokens, blended at three input tokens per output token.
- Which is faster, GPT-5.5 Pro or GPT-5.6 Luna?
- GPT-5.6 Luna streams faster: 124 against 4 output tokens per second.
- Which has the larger context window?
- Both accept 1.1M tokens of context.