gemma-3n-E2B-it: benchmark results
Provider: Google. Released 2025-06-26. Access: Open.
Unified ELO 1448 ± 1, rank #1339 of 2032 rated models, from 312 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Italian NLU - ScaLA IT | 45.3 | Linguistic acceptability Score (%) | 90.1 |
| EuroEval Portuguese NLU - ScaLA PT | 38.13 | Linguistic acceptability Score (%) | 88.6 |
| EuroEval Albanian NLU - MMS SQ | 27.45 | Sentiment classification Score (%) | 88.5 |
| EuroEval Portuguese NLU | 58.64 | NLU Average Score (%) | 85.9 |
| EuroEval Bosnian | 53.7 | Average Score (%) | 85.7 |
| EuroEval Norwegian NLU - Norec | 58.48 | Sentiment classification Score (%) | 85.7 |
| EuroEval French NLU - ScaLA FR | 48.12 | Linguistic acceptability Score (%) | 85.6 |
| EuroEval Italian NLU | 59.55 | NLU Average Score (%) | 83.1 |
| EuroEval Serbian NLU - MMS SR | 48.24 | Sentiment classification Score (%) | 82.2 |
| EuroEval Ukrainian NLU - Cross Domain UK Reviews | 60.94 | Sentiment classification Score (%) | 82 |
| EuroEval Hungarian NLU - HuSST | 55.31 | Sentiment classification Score (%) | 81.4 |
| EuroEval Danish NLU - Angry Tweets | 55.17 | Sentiment classification Score (%) | 81.1 |
Interactive version: theaggregate.ai/model?slug=gemma-3n-e2b-it · How It Works · Data refreshed daily, snapshot 2026-09-26.