gemma3:12B-it-fp16: benchmark results
Provider: Other.
Aggregate Rating 1594 ± 35, rank #1067 of 10916 rated models, from 79 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval French NLU - Allocine | 96.76 | Matthews correlation coefficient (%) | 97.3 |
| EuroEval Norwegian NLU - Norec | 62.27 | Matthews correlation coefficient (%) | 95.1 |
| EuroEval French NLU - Eltec | 72.66 | Micro F1 excluding MISC (%) | 94.7 |
| EuroEval Faroese NLU - FoQA | 75.27 | Character F1 (%) | 89.3 |
| EuroEval Icelandic NLU | 50.01 | NLU Average Score (%) | 88.6 |
| EuroEval Dutch NLU - CoNLL NL | 70.37 | Micro F1 excluding MISC (%) | 88.5 |
| EuroEval Italian NLU - SQuAD IT | 73.11 | Character F1 (%) | 88.5 |
| EuroEval Norwegian | 61.34 | Average Score (%) | 87.5 |
| EuroEval Icelandic NLU - ScaLA IS | 32.22 | Matthews correlation coefficient (%) | 85.4 |
| EuroEval Norwegian Knowledge | 43.85 | Knowledge Average Score (%) | 84.1 |
| EuroEval Icelandic NLU - Hotter and Colder Sentiment | 50.56 | Matthews correlation coefficient (%) | 82.9 |
| EuroEval French NLU | 67.76 | NLU Average Score (%) | 82.6 |
Interactive version: theaggregate.ai/model?slug=gemma3-12b-it-fp16 · How It Works · Data refreshed daily, snapshot 2026-11-08.