Luminous Extended (30B): benchmark results
Provider: Other. Access: API.
Aggregate Rating 1226 ± 25, rank #9443 of 10916 rated models, from 56 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM Classic - Dyck | 66.6 | Exact Match (%) | 76.5 |
| RealToxicityPrompts | 0.03 | Toxic fraction | 73.2 |
| HELM Classic - IMDB | 94.73 | Exact Match (%) | 68.9 |
| HELM Classic - WikiFact | 30.81 | Exact Match (%) | 66.7 |
| HELM Classic - BoolQ | 76.67 | Exact Match (%) | 62.1 |
| HELM Classic - MATH | 11.11 | Equivalent (%) | 58.8 |
| HELM Classic - XSUM | 12.37 | ROUGE-2 (%) | 56.1 |
| HELM Classic - NarrativeQA | 66.48 | F1 (%) | 55.4 |
| HELM Classic - GSM8K | 6.67 | Exact Match (%) | 54.4 |
| HELM Classic - Synthetic Reasoning Abstract | 22.52 | Exact Match (%) | 52.9 |
| HELM Classic - CNN/DailyMail | 13.89 | ROUGE-2 (%) | 51.2 |
| HELM Classic - bAbI | 47.46 | Exact Match (%) | 49.3 |
Interactive version: theaggregate.ai/model?slug=luminous-extended-30b · How It Works · Data refreshed daily, snapshot 2026-11-08.