GPT-5.6 Luna (High): benchmark results
GPT-5.6 Luna evaluated at the high reasoning-effort setting. Provider: OpenAI. Released 2026-07-09. Access: API.
Unified ELO 1681 ± 1, rank #148 of 1761 rated models, from 30 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| PM-LLM-Benchmark | 37.2 | Score | 93.4 |
| AA Long Context Reasoning | 80.33 | Accuracy (%) | 90.8 |
| AA CritPt | 16.57 | Accuracy (%) | 89.7 |
| Artificial Analysis Intelligence Index | 37.36 | Intelligence Index | 89 |
| AA Omniscience - Software Engineering (SWE) | 67.2 | Accuracy (%) | 88.9 |
| AA GPQA Diamond | 89.19 | Accuracy (%) | 86.7 |
| LLM Chess (Saplin) | 919.4 | ELO | 86.3 |
| AA Omniscience - Science, Engineering & Mathematics | 44.3 | Accuracy (%) | 85.2 |
| AA-Omniscience Accuracy | 41.78 | Accuracy (%) | 85.2 |
| AA Humanity's Last Exam | 33.41 | Accuracy (%) | 84.7 |
| AA Omniscience - Business | 33.9 | Accuracy (%) | 84.2 |
| AA Omniscience - Humanities & Social Sciences | 39.2 | Accuracy (%) | 83.9 |
Interactive version: theaggregate.ai/model?slug=gpt-5-6-luna-high · How It Works · Data refreshed daily, snapshot 2026-09-05.