Gemma 4 E4B (IT) (Non-reasoning): benchmark results
Provider: Google. Released 2026-04-02. Access: Open.
Aggregate Rating 1492 ± 20, rank #1113 of 2170 rated models, from 49 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| DAR-MGSM - Average - Localized | 78 | Accuracy (%) | 70 |
| DAR-MGSM - Average - Translated | 79.1 | Accuracy (%) | 70 |
| DAR-MGSM - Egyptian - Localized | 79.6 | Accuracy (%) | 70 |
| DAR-MGSM - Egyptian - Translated | 80 | Accuracy (%) | 70 |
| DAR-MGSM - Emirati - Localized | 83.2 | Accuracy (%) | 70 |
| DAR-MGSM - Emirati - Translated | 85.6 | Accuracy (%) | 70 |
| DAR-MGSM - Jordanian - Localized | 84 | Accuracy (%) | 70 |
| DAR-MGSM - Jordanian - Translated | 82.8 | Accuracy (%) | 70 |
| DAR-MGSM - MSA - Localized | 81.2 | Accuracy (%) | 70 |
| DAR-MGSM - MSA - Translated | 84.4 | Accuracy (%) | 70 |
| DAR-MGSM - Moroccan - Localized | 66.8 | Accuracy (%) | 70 |
| DAR-MGSM - Moroccan - Translated | 66.4 | Accuracy (%) | 70 |
Interactive version: theaggregate.ai/model?slug=gemma-4-e4b-it-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-05.