nb-gpt-j-6B-alpaca: benchmark results
NB-AiLab NB GPT-J 6B Alpaca is a Norwegian Bokmal instruction fine-tune of NB GPT-J 6B using the Norwegian Alpaca dataset. The publisher documents a Norwegian instruction/response prompt template; this release remains distinct from NB GPT-J base and v2. Provider: National Library of Norway. Access: Open.
Aggregate Rating 1158 ± 20, rank #9849 of 10916 rated models, from 74 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - College Physics | 32.35 | Accuracy (%) | 80.6 |
| MMLU-by-task - High School Statistics | 46.3 | Accuracy (%) | 78.9 |
| MMLU-by-task - Moral Scenarios | 27.26 | Accuracy (%) | 59.8 |
| MMLU-by-task - College Mathematics | 32 | Accuracy (%) | 53.7 |
| MMLU-by-task - High School Physics | 29.8 | Accuracy (%) | 46.5 |
| MMLU-by-task - College Computer Science | 35 | Accuracy (%) | 42 |
| MMLU-by-task - Professional Medicine | 44.12 | Accuracy (%) | 41 |
| MMLU-by-task - Abstract Algebra | 28 | Accuracy (%) | 39.6 |
| MMLU-by-task - Medical Genetics | 40 | Accuracy (%) | 37.8 |
| MMLU-by-task - College Biology | 34.72 | Accuracy (%) | 36.8 |
| MMLU-by-task - Security Studies | 38.78 | Accuracy (%) | 36.6 |
| MMLU-by-task - High School Geography | 35.86 | Accuracy (%) | 33.8 |
Interactive version: theaggregate.ai/model?slug=nb-gpt-j-6b-alpaca · How It Works · Data refreshed daily, snapshot 2026-11-08.