Llama 3.1 8B Dialog K2 Da: benchmark results
Provider: Meta.
Aggregate Rating 1396 ± 41, rank #6289 of 10916 rated models, from 9 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Danish NLU - Angry Tweets | 52.96 | Matthews correlation coefficient (%) | 72 |
| EuroEval Danish NLU - Multi Wiki QA DA | 69.3 | Character F1 (%) | 47 |
| EuroEval Swedish NLU - Multi Wiki QA SV | 62.47 | Character F1 (%) | 42.3 |
| EuroEval Danish NLU - ScaLA DA | 19.12 | Matthews correlation coefficient (%) | 42 |
| EuroEval Danish NLU | 37.9 | NLU Average Score (%) | 41.9 |
| EuroEval Danish Knowledge | 38.41 | Knowledge Average Score (%) | 41.7 |
| EuroEval Danish | 34.57 | Average Score (%) | 40.1 |
| EuroEval Danish Common Sense Reasoning | 16.91 | Common Sense Reasoning Average Score (%) | 36.2 |
| EuroEval Danish NLU - Dansk | 41.63 | Micro F1 excluding MISC (%) | 34.3 |
Interactive version: theaggregate.ai/model?slug=llama-3-1-8b-dialog-k2-da · How It Works · Data refreshed daily, snapshot 2026-11-08.