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 1900 ± 23, rank #65 of 1776 rated models, from 43 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Omniscience - Software Engineering (SWE) - PHP | 82 | Accuracy (%) | 97.2 |
| AA Omniscience - Software Engineering (SWE) - Swift | 80 | Accuracy (%) | 95.9 |
| AA Omniscience - Software Engineering (SWE) - TypeScript | 76.67 | Accuracy (%) | 95.8 |
| Artificial Analysis Intelligence Index | 46.06 | Intelligence Index | 95.2 |
| AA CritPt | 16.57 | Accuracy (%) | 94.7 |
| AA SciCode | 50.69 | Accuracy (%) | 94.2 |
| AA Omniscience - Software Engineering (SWE) - Python | 72 | Accuracy (%) | 93.9 |
| PM-LLM-Benchmark | 37.2 | Score | 93.7 |
| AA Omniscience - Software Engineering (SWE) - Go | 66 | Accuracy (%) | 93.1 |
| AA Omniscience - Software Engineering (SWE) - Kotlin | 60 | Accuracy (%) | 92 |
| AA Omniscience - Software Engineering (SWE) | 64.7 | Accuracy (%) | 91.9 |
| AA GPQA Diamond | 89.19 | Accuracy (%) | 91.7 |
Interactive version: theaggregate.ai/model?slug=gpt-5-6-luna-high · How the rankings work · Data refreshed daily, snapshot 2026-07-22.