Llama 3.2 1B Instruct — benchmark results
Instruction-tuned Llama 3.2 1B checkpoint. Provider: Meta. Released 2024-09-25. Access: Open.
Unified ELO 1207 ± 13, rank #1681 of 1776 rated models, from 438 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Japanese LLM - Wikicorpus J TO E Bleu EN | 36.92 | Score (%) | 97.8 |
| Open Japanese LLM - ALT J TO E Bleu EN | 19.03 | Score (%) | 91.8 |
| Open LLM Leaderboard - IFEval | 58.1 | Score | 69.9 |
| BlueBench - Summarization | 17.62 | Score (%) | 58.8 |
| LA Leaderboard - Spanish Law Exams | 31.09 | Accuracy (%) | 58.8 |
| EuroEval German Summarization - Mlsum DE | 31.75 | Score (%) | 48.6 |
| LA Leaderboard - EusExams Basque | 29.77 | Accuracy (%) | 44.7 |
| HELMET (128K) | 25 | Average Score | 42.7 |
| EuroEval Serbian Summarization - LR SUM SR | 24.26 | Score (%) | 42.2 |
| Open LLM Leaderboard - MATH Level 5 | 8.23 | Score | 41.7 |
| EuroEval Bosnian Summarization - LR SUM BS | 23.94 | Score (%) | 40.8 |
| EuroEval Albanian NLU - ScaLA SQ | 3.45 | Linguistic acceptability Score (%) | 40.5 |
Interactive version: theaggregate.ai/model?slug=llama-3-2-1b-instruct · How the rankings work · Data refreshed daily, snapshot 2026-07-22.