benchgap
Other · model

GEV-26B-Decide benchmark scores

As of 2026-10-29, GEV-26B-Decide (Other) has measured scores on 6 benchmarks and estimated scores on 4 more.

BenchmarkScoreSource
Decision Index Full Score53.5%measured
Decision Index Arts48.6%measured
Decision Index Knowledge38.7%measured
Decision Index Language55.9%measured
Decision Index Retrieval63.3%measured
Decision Index Tools66.3%measured
HLE-MultiChoice (Decision Index)17.3%estimated ± 2.0 pp, medium confidence
Artificial Analysis Decision Index54.1%estimated ± 3.7 pp, medium confidence
When2Call (Decision Index)79.3%estimated ± 3.5 pp, medium confidence
WildGuardTest (Decision Index)90.0%estimated ± 1.4 pp, medium confidence