GPT-6 Luna vs GPT-6 Sol
GPT-6 Luna Verdict
- GPT-6 Sol (max) leads on quality: 67.7 vs 61.2.
- GPT-6 Sol (max) is stronger in composite, knowledge, long context, multimodal, reasoning.
- GPT-6 Luna (max) is 20× cheaper ($0.200 vs $4.00 per 1M blended).
| Metric | GPT-6 Luna (max) | GPT-6 Sol (max) |
|---|---|---|
| BenchLeader Index | 61.2 | 67.7 |
| Composite score | 73.9 | 86.2 |
| Knowledge score | 63.2 | 75.4 |
| Long context score | 67.5 | 67.7 |
| Multimodal score | 59.2 | 67.1 |
| Reasoning score | 76.1 | 95.0 |
| Blended price $/M | $0.200 | $4.00 |
| Output speed | 157 tok/s | 126 tok/s |
| Time to first answer | 142.6 s | 107.2 s |
| Context window | 1.1M | 1.1M |
| AA Intelligence Index | 37.3 | 47.5 |
| AA-LCR | 83.3% | 83.7% |
| MMMU-Pro | 75.5% | 83.3% |
| AA-Omniscience | 0.7 | 27.1 |
| Humanity's Last Exam (AA) | 38.5% | 47.9% |
| SciCode (AA) | 54.6% | 57.6% |
| CritPt | 19.4% | 30.9% |
| GDPval (AA) | 43.4% | 49.4% |
| Terminal-Bench 4.0 (AA) | 12.6% | 43.9% |
| AutomationBench | 53.2% | 61.6% |
| GDP.pdf | 20.4% | 24.8% |
| MLCR | 16.1% | 16.1% |
| AA-Omniscience: accuracy | 43.8% | 54.5% |
| AA-Omniscience: non-hallucination | 23.3% | 39.9% |
| AA-Briefcase | 1299 | 1483 |
Data as of 2026-09-23. Best configuration of each model; every score links to its source on the model pages.
GPT-6 Luna vs GPT-6 Sol: questions
- Is GPT-6 Luna better than GPT-6 Sol?
- GPT-6 Sol (max) leads on quality: 67.7 vs 61.2. The BenchLeader Index combines every independent quality benchmark; GPT-6 Sol (max) is ahead overall as of 2026-09-23, but check the category scores for your use.
- Which is cheaper, GPT-6 Luna or GPT-6 Sol?
- GPT-6 Luna is cheaper: $0.200 against $4.00 per million tokens, blended at three input tokens per output token.
- Which is faster, GPT-6 Luna or GPT-6 Sol?
- GPT-6 Luna streams faster: 157 against 126 output tokens per second.
- Which has the larger context window?
- Both accept 1.1M tokens of context.