benchgap
Other · model

Drex v2.0 benchmark scores

As of 2026-10-29, Drex v2.0 (Other) has measured scores on 6 benchmarks and estimated scores on 4 more.

BenchmarkScoreSource
Decision Index Full Score52.8%measured
Decision Index Arts55.2%measured
Decision Index Knowledge36.0%measured
Decision Index Language52.7%measured
Decision Index Retrieval58.5%measured
Decision Index Tools72.5%measured
HLE-MultiChoice (Decision Index)17.3%estimated ± 2.0 pp, medium confidence
Artificial Analysis Decision Index59.3%estimated ± 3.7 pp, medium confidence
When2Call (Decision Index)89.7%estimated ± 3.5 pp, medium confidence
WildGuardTest (Decision Index)91.7%estimated ± 1.4 pp, medium confidence