Other · model
Mercury Decide benchmark scores
As of 2026-10-29, Mercury Decide (Other) has measured scores on 4 benchmarks and estimated scores on 6 more.
| Benchmark | Score | Source |
|---|---|---|
| Decision Index Full Score | 57.1% | estimated ± 4.5 pp, medium confidence |
| Decision Index Arts | 48.5% | estimated ± 2.0 pp, medium confidence |
| Decision Index Knowledge | 33.9% | estimated ± 3.6 pp, medium confidence |
| Decision Index Language | 41.1% | estimated ± 4.2 pp, medium confidence |
| Decision Index Retrieval | 61.6% | estimated ± 7.6 pp, low confidence |
| Decision Index Tools | 77.9% | estimated ± 3.0 pp, medium confidence |
| HLE-MultiChoice (Decision Index) | 10.1% | measured |
| Artificial Analysis Decision Index | 52.7% | measured |
| When2Call (Decision Index) | 79.3% | measured |
| WildGuardTest (Decision Index) | 88.0% | measured |