Llama 3.1 8B Laerebogen: benchmark results
Provider: Meta.
Aggregate Rating 1457 ± 42, rank #3462 of 10916 rated models, from 9 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Danish NLU - Angry Tweets | 53.37 | Matthews correlation coefficient (%) | 74.7 |
| EuroEval Danish NLU | 47.7 | NLU Average Score (%) | 55.9 |
| EuroEval Danish NLU - ScaLA DA | 30.82 | Matthews correlation coefficient (%) | 53.4 |
| EuroEval Danish | 43.12 | Average Score (%) | 49.3 |
| EuroEval Danish NLU - Multi Wiki QA DA | 69.55 | Character F1 (%) | 48.7 |
| EuroEval Danish NLU - Dansk | 48.91 | Micro F1 excluding MISC (%) | 47.6 |
| EuroEval Danish Knowledge | 46.31 | Knowledge Average Score (%) | 47.2 |
| EuroEval Swedish NLU - Multi Wiki QA SV | 61.99 | Character F1 (%) | 41.5 |
| EuroEval Danish Common Sense Reasoning | 22.37 | Common Sense Reasoning Average Score (%) | 40.4 |
Interactive version: theaggregate.ai/model?slug=llama-3-1-8b-laerebogen · How It Works · Data refreshed daily, snapshot 2026-11-08.