Gemma 2 9B — benchmark results
Google's 9B Gemma 2 base model (June 2024), pretrained via knowledge distillation from the 27B teacher for above-class performance. Provider: Google. Released 2024-06-27. Access: Open.
Unified ELO 1450 ± 15, rank #998 of 1776 rated models, from 140 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Shlepa - Movies MC (RU) | 50.46 | Accuracy (%) | 100 |
| EuroEval Swedish NLU - Swerec | 80.82 | Sentiment classification Score (%) | 98.8 |
| LA Leaderboard - EusExams Basque | 50.76 | Accuracy (%) | 97.9 |
| LA Leaderboard - PIQA Catalan | 70.24 | Accuracy (%) | 97.1 |
| LA Leaderboard - XNLI Galician | 50.11 | Accuracy (%) | 97.1 |
| EuroEval Norwegian NLU - Norec | 62.9 | Sentiment classification Score (%) | 96 |
| Shlepa - Law MC (RU) | 58.19 | Accuracy (%) | 94.1 |
| LA Leaderboard | 58.2 | Average Score (%) | 92.6 |
| EuroEval Icelandic NLU - NQII | 58.42 | Reading comprehension Score (%) | 92.4 |
| AILuminate Safety | 4 | Safety Grade (1-5) | 91.9 |
| EuroEval German NLU - Germanquad | 65.2 | Reading comprehension Score (%) | 89.7 |
| EuroEval French NLU - FQuAD | 73.09 | Reading comprehension Score (%) | 88.5 |
Interactive version: theaggregate.ai/model?slug=gemma-2-9b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.