gemma-7B: benchmark results
Provider: Google. Released 2024-02-21. Access: Open.
Unified ELO 1395 ± 1, rank #1156 of 1392 rated models, from 225 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| European LLM Leaderboard - Zero-Shot Accuracy | 56.69 | Average Accuracy (%) | 95.1 |
| EuroEval Icelandic NLU - NQII | 56.97 | Reading comprehension Score (%) | 90.1 |
| EuroEval French NLU - FQuAD | 72.77 | Reading comprehension Score (%) | 87.7 |
| EuroEval German NLU - Germanquad | 64.31 | Reading comprehension Score (%) | 87.2 |
| Open Medical LLM - MMLU College Biology | 79.86 | Accuracy (%) | 85.5 |
| EuroEval Norwegian NLU - Norquad | 72.02 | Reading comprehension Score (%) | 85.1 |
| EuroEval Spanish NLU - MLQA ES | 65.03 | Reading comprehension Score (%) | 83.1 |
| EuroEval Dutch NLU - SQuAD NL | 77.24 | Reading comprehension Score (%) | 82.7 |
| EuroEval Swedish NLU - Swerec | 78.08 | Sentiment classification Score (%) | 82.5 |
| Open Medical LLM - PubMedQA | 76.2 | Accuracy (%) | 82.1 |
| OpenBookQA | 78.6 | Accuracy (%) | 81 |
| EuroEval English NLU - SST-5 | 67.79 | Sentiment classification Score (%) | 77.2 |
Interactive version: theaggregate.ai/model?slug=gemma-7b · How It Works · Data refreshed daily, snapshot 2026-09-05.