Llama 3.2 1B: benchmark results
Provider: Meta. Released 2024-09-25. Access: Open.
Unified ELO 1315 ± 1, rank #1331 of 1392 rated models, from 497 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| CLEAR | 3.2 | Version (self-reported) | 100 |
| LA Leaderboard - GalCoLA | 53.19 | Accuracy (%) | 72.1 |
| Open Japanese LLM - Mbpp Pylint Check | 59.64 | Score (%) | 60.6 |
| Open Japanese LLM - CG | 10.44 | Score (%) | 50.8 |
| EuroEval Polish Summarization - PSC | 21.7 | Score (%) | 50.3 |
| MERA - ruHumanEval | 10.67 | pass@1 (%) | 48.1 |
| LA Leaderboard - AQuAS | 64.79 | Accuracy (%) | 45.6 |
| EuroEval Catalan NLU - Guia CAT | 54.46 | Sentiment classification Score (%) | 45 |
| MERA - ruCodeEval | 7.01 | pass@1 (%) | 44.5 |
| EuroEval Spanish Summarization - Mlsum ES | 23.3 | Score (%) | 42.2 |
| EuroEval Bosnian Summarization - LR SUM BS | 23.96 | Score (%) | 41.4 |
| EuroEval German Summarization - Mlsum DE | 30.99 | Score (%) | 41.2 |
Interactive version: theaggregate.ai/model?slug=llama-3-2-1b · How It Works · Data refreshed daily, snapshot 2026-09-05.