Gemma 3n E2B — benchmark results

Provider: Google. Released 2025-06-26. Access: Open.

Unified ELO 1323 ± 56, rank #1514 of 1839 rated models, from 18 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Turkish MMLU60Accuracy (%)55.4
Open PL LLM - RAG38.44Average RAG Score (%)26.2
Open PL LLM - Multiple Choice6.35Average Multiple-Choice Score (%)23.8
Open PL LLM - Generative14.06Average Generative Score (%)22.4
Open PL LLM Leaderboard10.71Average Score (%)22.4
AI for Education Pedagogy - Technology68.87Accuracy (%)21
AI for Education Pedagogy - Primary62.44Accuracy (%)15.8
AI for Education SEND60.55Accuracy (%)15.5
AI for Education Pedagogy - Maths53.17Accuracy (%)15.2
AI for Education Pedagogy - Secondary57.08Accuracy (%)14.3
AI for Education Pedagogy57.84Accuracy (%)14.1
AI for Education Pedagogy - Social studies54.55Accuracy (%)12.5

Interactive version: theaggregate.ai/model?slug=gemma-3n-e2b · How It Works · Data refreshed daily, snapshot 2026-08-05.