GPT-6 Luna (xHigh): benchmark results
Provider: OpenAI. Access: API.
Unified ELO 1705 ± 1, rank #148 of 3363 rated models, from 61 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA-Omniscience Index - Software Engineering (SWE) - Go | 60 | Omniscience Index | 92 |
| AA-Omniscience Index - Software Engineering (SWE) - Kotlin | 44 | Omniscience Index | 91.4 |
| AA-Omniscience Index - Software Engineering (SWE) - PHP | 60 | Omniscience Index | 91 |
| Artificial Analysis Intelligence Index | 33.88 | Intelligence Index | 88.7 |
| AA CritPt | 17.43 | Accuracy (%) | 88.5 |
| AA-Omniscience Index - Software Engineering (SWE) - HTML | 56 | Omniscience Index | 88.3 |
| AA-Omniscience Index - Software Engineering (SWE) - Rust | 64 | Omniscience Index | 88.3 |
| AA-Omniscience Index - Software Engineering (SWE) - Python | 49.5 | Omniscience Index | 88.2 |
| AA Long Context Reasoning | 80 | Accuracy (%) | 87.4 |
| AA-Omniscience Index - Software Engineering (SWE) - TypeScript | 50 | Omniscience Index | 87.2 |
| AA-Omniscience Index - Software Engineering (SWE) - JavaScript | 47.27 | Omniscience Index | 86.4 |
| AA-Omniscience Index - Software Engineering (SWE) | 38 | Omniscience Index | 85.9 |
Interactive version: theaggregate.ai/model?slug=gpt-6-luna-xhigh · How It Works · Data refreshed daily, snapshot 2026-09-23.