nesso-4B: benchmark results
Provider: mii-llm. Released 2025-04-01. Access: Open.
Aggregate Rating 1505 ± 28, rank #2262 of 10916 rated models, from 264 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Spanish NLU - ScaLA ES | 41.76 | Matthews correlation coefficient (%) | 92.2 |
| EuroEval Italian NLU - ScaLA IT | 50.97 | Matthews correlation coefficient (%) | 92.1 |
| EuroEval Slovene NLU - MultiWikiQA SL | 69.75 | Character F1 (%) | 92.1 |
| EuroEval Albanian NLU - MultiWikiQA SQ | 65.62 | Character F1 (%) | 91.5 |
| EuroEval Portuguese NLU | 61.67 | NLU Average Score (%) | 91.5 |
| EuroEval Polish NLU - PoQuAD | 59.43 | Character F1 (%) | 91.4 |
| EuroEval Serbian NLU - MultiWikiQA SR | 64.65 | Character F1 (%) | 91.2 |
| EuroEval Portuguese NLU - ScaLA PT | 43.18 | Matthews correlation coefficient (%) | 91.1 |
| EuroEval Italian NLU | 62.61 | NLU Average Score (%) | 90.6 |
| EuroEval Romanian NLU - MultiWikiQA RO | 73.57 | Character F1 (%) | 89.8 |
| EuroEval Icelandic NLU - NQII | 55.95 | Character F1 (%) | 87.5 |
| EuroEval Bulgarian NLU - MultiWikiQA BG | 74.16 | Character F1 (%) | 87.2 |
Interactive version: theaggregate.ai/model?slug=nesso-4b · How It Works · Data refreshed daily, snapshot 2026-11-08.