phi4:14B-q4_K_M: benchmark results
Provider: Other.
Aggregate Rating 1583 ± 30, rank #1206 of 10916 rated models, from 83 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval German NLU - Sb10K | 61.71 | Matthews correlation coefficient (%) | 98.2 |
| EuroEval Norwegian NLU - Norec | 64.05 | Matthews correlation coefficient (%) | 97.5 |
| EuroEval Icelandic NLU - NQII | 60.66 | Character F1 (%) | 95.3 |
| EuroEval German NLU | 60.08 | NLU Average Score (%) | 92.8 |
| EuroEval Italian NLU | 62.63 | NLU Average Score (%) | 90.9 |
| EuroEval Italian NLU - SQuAD IT | 73.52 | Character F1 (%) | 90.4 |
| EuroEval French NLU - Allocine | 95.39 | Matthews correlation coefficient (%) | 90.2 |
| EuroEval Italian | 63.06 | Average Score (%) | 89.2 |
| EuroEval Dutch NLU - CoNLL NL | 69.3 | Micro F1 excluding MISC (%) | 87 |
| EuroEval Dutch NLU - SQuAD NL | 78.16 | Character F1 (%) | 87 |
| EuroEval German NLU - Germanquad | 64.29 | Character F1 (%) | 86.9 |
| EuroEval Italian NLU - ScaLA IT | 40.57 | Matthews correlation coefficient (%) | 86.8 |
Interactive version: theaggregate.ai/model?slug=phi4-14b-q4-k-m · How It Works · Data refreshed daily, snapshot 2026-11-08.