gemma3:4B-it-q4_K_M: benchmark results
Provider: Other.
Aggregate Rating 1454 ± 35, rank #3568 of 10916 rated models, from 83 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Faroese NLU - FoSent | 46.03 | Matthews correlation coefficient (%) | 71.2 |
| EuroEval Faroese | 44.77 | Average Score (%) | 67.6 |
| EuroEval Icelandic NLU - ScaLA IS | 12.45 | Matthews correlation coefficient (%) | 65.5 |
| EuroEval Faroese NLU - FoQA | 66.35 | Character F1 (%) | 64 |
| EuroEval Norwegian NLU - Norec | 52.92 | Matthews correlation coefficient (%) | 63.4 |
| EuroEval Dutch NLU - CoNLL NL | 61.04 | Micro F1 excluding MISC (%) | 63.1 |
| EuroEval Italian NLU - Sentipolc16 | 55.85 | Matthews correlation coefficient (%) | 63 |
| EuroEval Faroese NLU - ScaLA FO | 6.49 | Matthews correlation coefficient (%) | 62.5 |
| EuroEval Danish NLU - Angry Tweets | 50.34 | Matthews correlation coefficient (%) | 62.1 |
| EuroEval Icelandic NLU - Hotter and Colder Sentiment | 38.35 | Matthews correlation coefficient (%) | 61.5 |
| EuroEval English NLU - SST-5 | 66.22 | Matthews correlation coefficient (%) | 60.5 |
| EuroEval Danish NLU - Dansk | 54.4 | Micro F1 excluding MISC (%) | 59.2 |
Interactive version: theaggregate.ai/model?slug=gemma3-4b-it-q4-k-m · How It Works · Data refreshed daily, snapshot 2026-11-08.