benchgap
Other · model

open-jev (pngwn) benchmark scores

As of 2026-10-29, open-jev (pngwn) (Other) has measured scores on 6 benchmarks and estimated scores on 4 more.

BenchmarkScoreSource
Decision Index Full Score31.1%measured
Decision Index Arts20.3%measured
Decision Index Knowledge23.9%measured
Decision Index Language36.9%measured
Decision Index Retrieval24.0%measured
Decision Index Tools36.7%measured
HLE-MultiChoice (Decision Index)9.6%estimated ± 2.0 pp, low confidence
Artificial Analysis Decision Index26.8%estimated ± 3.7 pp, low confidence
When2Call (Decision Index)34.8%estimated ± 3.5 pp, low confidence
WildGuardTest (Decision Index)88.4%estimated ± 1.7 pp, low confidence