Gemma 3 270M — benchmark results
Provider: Google. Released 2025-03-12. Access: Open.
Unified ELO 1150 ± 18, rank #1735 of 1776 rated models, from 308 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AI Energy Score (Text Generation) | 5 | Energy Score (1-5) | 79.5 |
| AA Omniscience | -31.32 | Score | 62.6 |
| EuroEval Bosnian Summarization - LR SUM BS | 20.18 | Score (%) | 34.2 |
| EuroEval Serbian Summarization - LR SUM SR | 19.58 | Score (%) | 33.3 |
| CritPt | 0 | Accuracy (self-reported) | 30.3 |
| EuroEval Lithuanian Common Sense Reasoning | 0.7 | Common Sense Reasoning Average Score (%) | 28 |
| AA CritPt | 0 | Accuracy (%) | 27.1 |
| EuroEval Slovene Common Sense Reasoning | 1.25 | Common Sense Reasoning Average Score (%) | 25.8 |
| EuroEval Faroese NLU - FoSent | 5.04 | Sentiment classification Score (%) | 24.8 |
| EuroEval Icelandic NLU - ScaLA IS | 0.02 | Linguistic acceptability Score (%) | 24.3 |
| EuroEval Dutch Simplification - Duidelijke Taal | 38.54 | Score (%) | 22.4 |
| EuroEval Albanian Summarization - LR SUM SQ | 20.74 | Score (%) | 21.6 |
Interactive version: theaggregate.ai/model?slug=gemma-3-270m · How the rankings work · Data refreshed daily, snapshot 2026-07-22.