roberta_jan_128_ncc: benchmark results
NB-AiLab roberta_jan_128_ncc is a roberta masked-language checkpoint published by the National Library of Norway lab. Its exact checkpoint label is retained for evaluation and downstream adaptation. Provider: National Library of Norway. Access: Open.
Aggregate Rating 1334 ± 39, rank #8087 of 10916 rated models, from 29 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Norwegian NLU - NorNE NN | 75.47 | Micro F1 excluding MISC (%) | 84 |
| EuroEval Norwegian NLU - NorNE NB | 76.02 | Micro F1 excluding MISC (%) | 80 |
| EuroEval Faroese NLU - FONE | 71.56 | Micro F1 excluding MISC (%) | 72.5 |
| EuroEval Swedish NLU - SUC3 | 56.2 | Micro F1 excluding MISC (%) | 53.1 |
| EuroEval Norwegian | 29.65 | Average Score (%) | 41 |
| EuroEval Icelandic NLU - Hotter and Colder Sentiment | 25.19 | Matthews correlation coefficient (%) | 40.8 |
| EuroEval Icelandic NLU - MIM-GOLD NER | 36.95 | Micro F1 excluding MISC (%) | 34.3 |
| EuroEval Faroese NLU - ScaLA FO | 0.99 | Matthews correlation coefficient (%) | 34.1 |
| EuroEval Icelandic | 19.08 | Average Score (%) | 32.7 |
| EuroEval Swedish | 35.64 | Average Score (%) | 31.9 |
| EuroEval Norwegian NLU - ScaLA NN | 5 | Matthews correlation coefficient (%) | 31.3 |
| EuroEval Norwegian NLU - ScaLA NB | 7.43 | Matthews correlation coefficient (%) | 29.3 |
Interactive version: theaggregate.ai/model?slug=roberta-jan-128-ncc · How It Works · Data refreshed daily, snapshot 2026-11-08.