benchgap
Other · model

Sifr 0.8B v3.1 benchmark scores

As of 2026-10-29, Sifr 0.8B v3.1 (Other) has measured scores on 6 benchmarks and estimated scores on 4 more.

BenchmarkScoreSource
Decision Index Full Score14.5%measured
Decision Index Arts8.7%measured
Decision Index Knowledge8.0%measured
Decision Index Language14.3%measured
Decision Index Retrieval26.0%measured
Decision Index Tools31.3%measured
HLE-MultiChoice (Decision Index)10.1%estimated ± 3.0 pp, low confidence
Artificial Analysis Decision Index34.3%estimated ± 6.6 pp, low confidence
When2Call (Decision Index)63.8%estimated ± 8.9 pp, low confidence
WildGuardTest (Decision Index)87.0%estimated ± 4.6 pp, low confidence