Other · model
Winnow-E4B benchmark scores
As of 2026-10-29, Winnow-E4B (Other) has measured scores on 6 benchmarks and estimated scores on 4 more.
| Benchmark | Score | Source |
|---|---|---|
| Decision Index Full Score | 32.7% | measured |
| Decision Index Arts | 28.2% | measured |
| Decision Index Knowledge | 20.1% | measured |
| Decision Index Language | 37.5% | measured |
| Decision Index Retrieval | 40.8% | measured |
| Decision Index Tools | 53.5% | measured |
| HLE-MultiChoice (Decision Index) | 9.6% | estimated ± 2.0 pp, low confidence |
| Artificial Analysis Decision Index | 35.4% | estimated ± 3.7 pp, low confidence |
| When2Call (Decision Index) | 47.2% | estimated ± 3.5 pp, low confidence |
| WildGuardTest (Decision Index) | 85.5% | estimated ± 1.4 pp, low confidence |