Llama 2 13B Chat Norwegian: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1364 ± 38, rank #7325 of 10916 rated models, from 27 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Dutch NLU - CoNLL NL | 57.66 | Micro F1 excluding MISC (%) | 52 |
| EuroEval English NLU - SQuAD | 79.57 | Character F1 (%) | 50.6 |
| EuroEval Faroese NLU - FONE | 60.54 | Micro F1 excluding MISC (%) | 48.5 |
| EuroEval Icelandic NLU - ScaLA IS | 3.14 | Matthews correlation coefficient (%) | 47.6 |
| EuroEval English NLU - SST-5 | 64.14 | Matthews correlation coefficient (%) | 46.1 |
| EuroEval Icelandic NLU - NQII | 43.44 | Character F1 (%) | 45.7 |
| EuroEval Danish Knowledge | 42.62 | Knowledge Average Score (%) | 44.2 |
| EuroEval Icelandic | 24.98 | Average Score (%) | 43.3 |
| EuroEval English NLU | 59.18 | NLU Average Score (%) | 41.2 |
| EuroEval Norwegian Common Sense Reasoning | 36.36 | Common Sense Reasoning Average Score (%) | 41.1 |
| EuroEval English NLU - CoNLL EN | 64.93 | Micro F1 excluding MISC (%) | 41 |
| EuroEval Danish Knowledge - Danish Citizen Tests | 42.62 | MCC (x100) | 38.9 |
Interactive version: theaggregate.ai/model?slug=llama-2-13b-chat-norwegian · How It Works · Data refreshed daily, snapshot 2026-11-08.