nb-roberta-base-ncc-plus-scandi-2e4: benchmark results
NB-AiLab nb-roberta-base-ncc-plus-scandi-2e4 is a xlm-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 1654 ± 40, rank #594 of 10916 rated models, from 29 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Norwegian NLU - NorNE NB | 90.37 | Micro F1 excluding MISC (%) | 99.7 |
| EuroEval Norwegian NLU - NorNE NN | 86.75 | Micro F1 excluding MISC (%) | 99.7 |
| EuroEval Faroese NLU - FONE | 88.84 | Micro F1 excluding MISC (%) | 99 |
| EuroEval Danish NLU - Dansk | 68.87 | Micro F1 excluding MISC (%) | 96.8 |
| EuroEval Icelandic NLU - MIM-GOLD NER | 79.99 | Micro F1 excluding MISC (%) | 96.7 |
| EuroEval Swedish | 73.34 | Average Score (%) | 95.6 |
| EuroEval Swedish NLU - SUC3 | 78.06 | Micro F1 excluding MISC (%) | 94.8 |
| EuroEval Swedish NLU | 73.34 | NLU Average Score (%) | 94.1 |
| EuroEval Norwegian | 67 | Average Score (%) | 93.9 |
| EuroEval Swedish NLU - ScaLA SV | 67.77 | Matthews correlation coefficient (%) | 92.6 |
| EuroEval Norwegian NLU | 67 | NLU Average Score (%) | 92.2 |
| EuroEval Norwegian NLU - ScaLA NB | 66.81 | Matthews correlation coefficient (%) | 90.7 |
Interactive version: theaggregate.ai/model?slug=nb-roberta-base-ncc-plus-scandi-2e4 · How It Works · Data refreshed daily, snapshot 2026-11-08.