Gemma 4 E2B (IT) (Non-reasoning): benchmark results
Provider: Google. Released 2026-04-02. Access: Open.
Aggregate Rating 1397 ± 23, rank #1469 of 2170 rated models, from 43 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| DAR-MGSM - Average - Localized | 64.7 | Accuracy (%) | 60 |
| DAR-MGSM - Egyptian - Localized | 69.2 | Accuracy (%) | 60 |
| DAR-MGSM - MSA - Localized | 71.6 | Accuracy (%) | 60 |
| DAR-MGSM - Saudi - Translated | 63.2 | Accuracy (%) | 60 |
| DAR-MGSM - Emirati - Localized | 74 | Accuracy (%) | 55 |
| DAR-MGSM - Emirati - Translated | 73.2 | Accuracy (%) | 50 |
| DAR-MGSM - Jordanian - Localized | 66.8 | Accuracy (%) | 50 |
| DAR-MGSM - MSA - Translated | 73.6 | Accuracy (%) | 50 |
| DAR-MGSM - Saudi - Localized | 61.6 | Accuracy (%) | 50 |
| DAR-MGSM - Average - Translated | 65.8 | Accuracy (%) | 45 |
| DAR-MGSM - Egyptian - Translated | 66.8 | Accuracy (%) | 40 |
| FrameBench - Frame Identification - English | 74 | Accuracy (%; FrameNet candidate frames) | 36.8 |
Interactive version: theaggregate.ai/model?slug=gemma-4-e2b-it-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-05.