OpenAI · model
GPT-6 Luna (Decisions) benchmark scores
As of 2026-11-18, GPT-6 Luna (Decisions) (OpenAI) has measured scores on 1 benchmark and estimated scores on 10 more.
| Benchmark | Score | Source |
|---|---|---|
| Decision Index Full Score | 51.4% | estimated ± 2.5 pp, high confidence |
| Decision Index Arts | 44.7% | estimated ± 4.5 pp, high confidence |
| Decision Index Knowledge | 34.9% | estimated ± 3.5 pp, high confidence |
| Decision Index Language | 51.7% | estimated ± 5.6 pp, medium confidence |
| Decision Index Retrieval | 59.8% | estimated ± 2.6 pp, high confidence |
| Decision Index Tools | 73.6% | estimated ± 4.7 pp, high confidence |
| HLE-MultiChoice (Decision Index) | 11.5% | estimated ± 2.1 pp, high confidence |
| Artificial Analysis Decision Index v1.0 | 51.3% | estimated ± 4.0 pp, high confidence |
| Artificial Analysis Decision Index | 60.2% | measured |
| When2Call (Decision Index) | 75.5% | estimated ± 5.5 pp, medium confidence |
| WildGuardTest (Decision Index) | 89.9% | estimated ± 2.2 pp, high confidence |