benchgap
Other · model

vLLM-SR Decision 2.0 Eos 0.8B benchmark scores

As of 2026-10-29, vLLM-SR Decision 2.0 Eos 0.8B (Other) has measured scores on 6 benchmarks and estimated scores on 4 more.

BenchmarkScoreSource
Decision Index Full Score18.4%measured
Decision Index Arts9.6%measured
Decision Index Knowledge7.6%measured
Decision Index Language19.7%measured
Decision Index Retrieval33.1%measured
Decision Index Tools29.2%measured
HLE-MultiChoice (Decision Index)10.1%estimated ± 3.0 pp, low confidence
Artificial Analysis Decision Index45.1%estimated ± 5.4 pp, low confidence
When2Call (Decision Index)37.4%estimated ± 6.8 pp, low confidence
WildGuardTest (Decision Index)84.8%estimated ± 1.7 pp, low confidence