Gemma 2 2B (IT) — benchmark results
Instruction-tuned Gemma 2 2B checkpoint. Provider: Google. Released 2024-06-27. Access: Open.
Unified ELO 1356 ± 8, rank #1392 of 1776 rated models, from 365 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SeaEval - Dialogue - SAMSum (Zero-Shot) | 31.12 | Average ROUGE (0-100) | 100 |
| SeaEval - Dialogue - DialogSum (Zero-Shot) | 25.97 | Average ROUGE (0-100) | 95.7 |
| LA Leaderboard - AQuAS | 68.53 | Accuracy (%) | 83.8 |
| Open Korean LLM Leaderboard | 443.88 | Average Score (%) | 81.8 |
| EuroEval English NLU - SST-5 | 67.9 | Sentiment classification Score (%) | 79.2 |
| LA Leaderboard - EusExams Basque | 35.76 | Accuracy (%) | 78.7 |
| Open Japanese LLM - Wiki NER SET F1 | 9.73 | Score (%) | 76.1 |
| OpenEval - BBQ | 80.38 | Exact Match (%) | 75.9 |
| EuroEval Icelandic NLU - NQII | 51.87 | Reading comprehension Score (%) | 75.2 |
| EuroEval German NLU - Germanquad | 56.63 | Reading comprehension Score (%) | 72.8 |
| Open LLM Leaderboard - IFEval | 56.68 | Score | 68.5 |
| Open CoT - LogiQA | 5.27 | CoT Gain (%) | 65.6 |
Interactive version: theaggregate.ai/model?slug=gemma-2-2b-it · How the rankings work · Data refreshed daily, snapshot 2026-07-22.