benchgap
Other · model

Jevstral 8B benchmark scores

As of 2026-10-29, Jevstral 8B (Other) has measured scores on 6 benchmarks and estimated scores on 4 more.

BenchmarkScoreSource
Decision Index Full Score32.2%measured
Decision Index Arts17.6%measured
Decision Index Knowledge22.5%measured
Decision Index Language37.3%measured
Decision Index Retrieval36.6%measured
Decision Index Tools57.6%measured
HLE-MultiChoice (Decision Index)9.4%estimated ± 2.2 pp, low confidence
Artificial Analysis Decision Index46.8%estimated ± 4.5 pp, low confidence
When2Call (Decision Index)52.3%estimated ± 5.9 pp, low confidence
WildGuardTest (Decision Index)87.1%estimated ± 1.4 pp, low confidence