emma-500-llama2-7B: benchmark results
Provider: MaLA-LM. Released 2024-05-01. Access: Open.
Aggregate Rating 1359 ± 38, rank #7468 of 10916 rated models, from 64 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval French NLU - FQuAD | 70.79 | Character F1 (%) | 79.9 |
| EuroEval English NLU - SQuAD | 83.69 | Character F1 (%) | 77.9 |
| EuroEval German NLU - Germanquad | 58.29 | Character F1 (%) | 76.9 |
| EuroEval Swedish NLU - Swerec | 77.4 | Matthews correlation coefficient (%) | 75.5 |
| EuroEval Norwegian NLU - Norquad | 68.63 | Character F1 (%) | 67.5 |
| EuroEval Dutch NLU - SQuAD NL | 74.27 | Character F1 (%) | 61.1 |
| EuroEval Icelandic NLU - NQII | 47.07 | Character F1 (%) | 53.8 |
| EuroEval Portuguese NLU - MultiWikiQA PT | 69.42 | Character F1 (%) | 53.5 |
| EuroEval Icelandic NLU - ScaLA IS | 5.45 | Matthews correlation coefficient (%) | 51.6 |
| EuroEval French | 52.6 | Average Score (%) | 48.9 |
| EuroEval Dutch | 50.87 | Average Score (%) | 46.8 |
| EuroEval Portuguese NLU - SST-2 PT | 75.07 | Matthews correlation coefficient (%) | 45.6 |
Interactive version: theaggregate.ai/model?slug=emma-500-llama2-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.