baseline-7-8b_1t-tokens_llama: benchmark results
Provider: Other.
Aggregate Rating 1244 ± 37, rank #9294 of 10916 rated models, from 41 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Dutch NLU - DBRD | 84.1 | Matthews correlation coefficient (%) | 39.6 |
| EuroEval Spanish NLU - MLQA ES | 55.05 | Character F1 (%) | 38.1 |
| EuroEval Portuguese NLU - HAREM | 37.36 | Micro F1 excluding MISC (%) | 37.8 |
| EuroEval Spanish NLU - ScaLA ES | 2.86 | Matthews correlation coefficient (%) | 35 |
| EuroEval Italian NLU - SQuAD IT | 53.91 | Character F1 (%) | 34.7 |
| EuroEval Finnish NLU - Tydiqa FI | 56.14 | Character F1 (%) | 34.6 |
| EuroEval Portuguese NLU - MultiWikiQA PT | 60.9 | Character F1 (%) | 34.3 |
| EuroEval Portuguese NLU | 41.84 | NLU Average Score (%) | 31.9 |
| EuroEval Portuguese NLU - SST-2 PT | 66.8 | Matthews correlation coefficient (%) | 31.4 |
| EuroEval Finnish NLU - Turku NER FI | 39.42 | Micro F1 excluding MISC (%) | 27.3 |
| EuroEval Norwegian Knowledge - Idioms NO | 0.39 | MCC (x100) | 26.9 |
| EuroEval Portuguese NLU - ScaLA PT | 2.32 | Matthews correlation coefficient (%) | 26.2 |
Interactive version: theaggregate.ai/model?slug=baseline-7-8b-1t-tokens-llama · How It Works · Data refreshed daily, snapshot 2026-11-08.