GPT-5.6 Luna (Low) — benchmark results
Provider: OpenAI. Released 2026-07-09. Access: API.
Unified ELO 1783 ± 19, rank #156 of 1744 rated models, from 35 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Omniscience - Software Engineering (SWE) - TypeScript | 72.22 | Accuracy (%) | 94.2 |
| AA Omniscience - Software Engineering (SWE) - Kotlin | 64 | Accuracy (%) | 93.4 |
| AA Omniscience - Software Engineering (SWE) - PHP | 70 | Accuracy (%) | 92.7 |
| AA Omniscience - Software Engineering (SWE) - Python | 67.5 | Accuracy (%) | 92.3 |
| AA Omniscience - Software Engineering (SWE) - Go | 64 | Accuracy (%) | 91.7 |
| AA Omniscience - Software Engineering (SWE) - C | 73 | Accuracy (%) | 90.3 |
| AA Omniscience - Software Engineering (SWE) | 62.1 | Accuracy (%) | 90.2 |
| AA Omniscience - Software Engineering (SWE) - JavaScript | 66.36 | Accuracy (%) | 90.2 |
| AA Omniscience - Software Engineering (SWE) - R | 50 | Accuracy (%) | 90 |
| AA Omniscience - Software Engineering (SWE) - Swift | 68 | Accuracy (%) | 89.2 |
| AA Omniscience - Software Engineering (SWE) - Rust | 72 | Accuracy (%) | 88.8 |
| AA-Omniscience Accuracy | 38.63 | Accuracy (%) | 87.5 |
Interactive version: aibenchmarks.dev/model?slug=gpt-5-6-luna-low · How the rankings work · Data refreshed daily, snapshot 2026-07-10.