Luminous Base (13B): benchmark results
Provider: Aleph Alpha. Released 2022-04-14. Access: API.
Aggregate Rating 1159 ± 25, rank #9839 of 10916 rated models, from 56 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM Classic - LSAT | 23.48 | Exact Match (%) | 92.6 |
| HELM Lite - LegalBench - International Citizenship Questions | 60.1 | Exact Match (%) | 75.6 |
| RealToxicityPrompts | 0.03 | Toxic fraction | 75.6 |
| HELM Classic - IMDB | 93.93 | Exact Match (%) | 57.6 |
| HELM Classic - WikiFact | 27.53 | Exact Match (%) | 54.5 |
| HELM Classic - CivilComments | 54.39 | Exact Match (%) | 48.5 |
| HELM Classic - Synthetic Reasoning Abstract | 20.88 | Exact Match (%) | 45.6 |
| HELM Classic - XSUM | 10.46 | ROUGE-2 (%) | 43.9 |
| HELM Classic - MATH | 8.85 | Equivalent (%) | 41.2 |
| HELM Classic - QuAC | 33.43 | F1 (%) | 40 |
| HELM Classic - Dyck | 51.67 | Exact Match (%) | 38.2 |
| HELM Classic - BoolQ | 71.87 | Exact Match (%) | 37.9 |
Interactive version: theaggregate.ai/model?slug=luminous-base-13b · How It Works · Data refreshed daily, snapshot 2026-11-08.