GPT-5.6 Luna (Low): benchmark results
GPT-5.6 Luna evaluated at the low reasoning-effort setting. Provider: OpenAI. Released 2026-07-09. Access: API.
Unified ELO 1631 ± 1, rank #313 of 1761 rated models, from 28 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Omniscience - Software Engineering (SWE) | 63.8 | Accuracy (%) | 86 |
| AA-Omniscience Accuracy | 39.62 | Accuracy (%) | 82.7 |
| AA Omniscience - Business | 32.4 | Accuracy (%) | 82.4 |
| AA Omniscience - Health | 36 | Accuracy (%) | 81.3 |
| AA Omniscience - Science, Engineering & Mathematics | 41.9 | Accuracy (%) | 80.9 |
| AA Omniscience - Humanities & Social Sciences | 34.9 | Accuracy (%) | 79.5 |
| AA Omniscience - Law | 28.7 | Accuracy (%) | 79.3 |
| Artificial Analysis Intelligence Index | 25.75 | Intelligence Index | 73.6 |
| AA GPQA Diamond | 83.54 | Accuracy (%) | 73.5 |
| AA CritPt | 2.57 | Accuracy (%) | 72.1 |
| AA Humanity's Last Exam | 19.83 | Accuracy (%) | 72.1 |
| AA Omniscience | -14.65 | Score | 68.6 |
Interactive version: theaggregate.ai/model?slug=gpt-5-6-luna-low · How It Works · Data refreshed daily, snapshot 2026-09-05.