Pleias-Pico: benchmark results
Provider: Pleias. Released 2024-11-24. Access: Open.
Aggregate Rating 1210 ± 38, rank #9551 of 10916 rated models, from 34 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Norwegian Knowledge - Idioms NO | 0.46 | MCC (x100) | 28.6 |
| EuroEval Italian NLU - ScaLA IT | 1.81 | Matthews correlation coefficient (%) | 20.3 |
| EuroEval Spanish NLU - ScaLA ES | 0.1 | Matthews correlation coefficient (%) | 20.2 |
| EuroEval Icelandic Knowledge | 1.15 | Knowledge Average Score (%) | 19.9 |
| EuroEval Spanish NLU - MLQA ES | 21.46 | Character F1 (%) | 15.6 |
| EuroEval Danish Knowledge | 4.56 | Knowledge Average Score (%) | 15.3 |
| EuroEval Italian Common Sense Reasoning | 0.2 | Common Sense Reasoning Average Score (%) | 13 |
| EuroEval Italian NLU - SQuAD IT | 17.73 | Character F1 (%) | 12.6 |
| EuroEval Danish Knowledge - Danish Citizen Tests | 4.56 | MCC (x100) | 12.1 |
| EuroEval Portuguese Common Sense Reasoning | 0.34 | Common Sense Reasoning Average Score (%) | 11.5 |
| EuroEval Spanish NLU - CoNLL ES | 32.21 | Micro F1 excluding MISC (%) | 11.2 |
| EuroEval Italian NLU - MultiNERD IT | 27 | Micro F1 excluding MISC (%) | 10.8 |
Interactive version: theaggregate.ai/model?slug=pleias-pico · How It Works · Data refreshed daily, snapshot 2026-11-08.