gemma-3n-E2B-it Instruct — benchmark results
Provider: Google. Released 2025-06-26. Access: Open.
Unified ELO 1253 ± 45, rank #1611 of 1776 rated models, from 42 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM Stats (ECLeKTic) | 2.5 | Score (%) | 35.7 |
| AA MATH-500 | 69.13 | Accuracy (%) | 27.7 |
| AA CritPt | 0 | Accuracy (%) | 27.1 |
| AA Omniscience - Software Engineering (SWE) - Dart | 12 | Accuracy (%) | 20.8 |
| AA Omniscience - Software Engineering (SWE) - Kotlin | 8 | Accuracy (%) | 15.1 |
| AA AIME 2025 | 10.33 | Accuracy (%) | 13.9 |
| AA Terminal-Bench Hard | 0.76 | Accuracy (%) | 12.8 |
| AA Omniscience - Software Engineering (SWE) - Go | 6 | Accuracy (%) | 12.5 |
| LLM Stats (HiddenMath) | 27.7 | Score (%) | 12.5 |
| AA Humanity's Last Exam | 3.99 | Accuracy (%) | 11.9 |
| LLM Stats (WMT24++) | 42.7 | Score (%) | 11.4 |
| AA Omniscience - Software Engineering (SWE) - Python | 8.5 | Accuracy (%) | 11 |
Interactive version: theaggregate.ai/model?slug=gemma-3n-e2b-it-instruct · How the rankings work · Data refreshed daily, snapshot 2026-07-22.