GPT-6 Luna (Medium): benchmark results
Provider: OpenAI. Access: API.
Unified ELO 1684 ± 1, rank #215 of 3363 rated models, from 62 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA-Omniscience Index - Software Engineering (SWE) - Kotlin | 42 | Omniscience Index | 90.3 |
| AA-Omniscience Index - Software Engineering (SWE) - JavaScript | 50.91 | Omniscience Index | 88.6 |
| AA-Omniscience Index - Software Engineering (SWE) - Rust | 64 | Omniscience Index | 88.3 |
| AA-Omniscience Index - Software Engineering (SWE) - Python | 48 | Omniscience Index | 87.7 |
| AA-Omniscience Index - Software Engineering (SWE) - Go | 48 | Omniscience Index | 87.2 |
| AA-Omniscience Index - Software Engineering (SWE) - TypeScript | 48.89 | Omniscience Index | 86.9 |
| AA-Omniscience Index - Software Engineering (SWE) - PHP | 48 | Omniscience Index | 86.7 |
| AA-Omniscience Index - Software Engineering (SWE) | 36.2 | Omniscience Index | 84.8 |
| AA-Omniscience Index - Software Engineering (SWE) - HTML | 50 | Omniscience Index | 84.6 |
| AA-Omniscience Accuracy | 43.13 | Accuracy (%) | 84.5 |
| Artificial Analysis Intelligence Index | 29.46 | Intelligence Index | 84.5 |
| AA CritPt | 10.57 | Accuracy (%) | 82.9 |
Interactive version: theaggregate.ai/model?slug=gpt-6-luna-medium · How It Works · Data refreshed daily, snapshot 2026-09-23.