Llama 2 13B Base: benchmark results
Provider: Meta. Released 2023-07-18. Access: Open.
Unified ELO 1383 ± 1, rank #1189 of 1392 rated models, from 131 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Portuguese NLU - MultiWikiQA PT | 76.05 | Reading comprehension Score (%) | 88.9 |
| EuroEval Italian NLU - SQuAD IT | 71.05 | Reading comprehension Score (%) | 76.8 |
| EuroEval Dutch NLU - DBRD | 90.19 | Sentiment classification Score (%) | 72.6 |
| EuroEval Spanish NLU - MLQA ES | 63.41 | Reading comprehension Score (%) | 72.4 |
| EuroEval Portuguese NLU - SST-2 PT | 80.59 | Sentiment classification Score (%) | 70.5 |
| Open Japanese LLM - Wiki Dependency SET F1 | 36.98 | Score (%) | 68 |
| URIAL-Bench - Writing | 7.53 | Judge Score (0-10) | 61.1 |
| MERA - CheGeKa | 17.45 | F1 (%) | 53.6 |
| EuroEval Portuguese NLU | 50.31 | NLU Average Score (%) | 52.7 |
| URIAL-Bench - Extraction | 4.7 | Judge Score (0-10) | 50 |
| MERA - ruCodeEval | 8.66 | pass@1 (%) | 47.8 |
| EuroEval Danish Knowledge | 46.76 | Knowledge Average Score (%) | 47.7 |
Interactive version: theaggregate.ai/model?slug=llama-2-13b-base · How It Works · Data refreshed daily, snapshot 2026-09-05.