Gemma 2 9B (IT): benchmark results
Instruction-tuned Gemma 2 9B checkpoint. Provider: Google. Released 2024-06-27. Access: Open.
Unified ELO 1442 ± 1, rank #978 of 1392 rated models, from 536 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LA Leaderboard - Spanish Law Exams | 47.9 | Accuracy (%) | 100 |
| LMArena Preference Proxy | 64.63 | Evaluator Accuracy (%) | 100 |
| Mobile-MMLU | 75 | Overall Accuracy (%) | 100 |
| SeaEval - Emotion - IndoEmotion (Zero-Shot) | 74.77 | Accuracy (%) | 100 |
| LA Leaderboard | 63.33 | Average Score (%) | 98.5 |
| LA Leaderboard - AQuAS | 71.86 | Accuracy (%) | 98.5 |
| LA Leaderboard - GalCoLA | 66.65 | Accuracy (%) | 98.5 |
| Open Korean LLM Leaderboard | 49.74 | Average Score (%) | 97.8 |
| Pinocchio Italian - Cultura | 72.72 | Accuracy (%) | 97.7 |
| Pinocchio Italian - Generale | 68.75 | Accuracy (%) | 97.7 |
| LA Leaderboard - COPA Spanish | 89.4 | Accuracy (%) | 97.1 |
| EuroEval Faroese NLU - FoQA | 78.56 | Reading comprehension Score (%) | 96.9 |
Interactive version: theaggregate.ai/model?slug=gemma-2-9b-it · How It Works · Data refreshed daily, snapshot 2026-09-05.