Llama-3-ELYZA-JP-8B: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1488 ± 29, rank #2530 of 10916 rated models, from 61 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Japanese LLM - Wiki PAS SET F1 | 8.48 | Score (%) | 81.4 |
| Open Japanese LLM - AIO Char F1 | 61.79 | Score (%) | 76.2 |
| Open Japanese LLM - Xlsum JA RougeLsum | 24.72 | Score (%) | 75 |
| Open Japanese LLM - Xlsum JA Bert Score JA F1 | 69.86 | Score (%) | 74.3 |
| Open Japanese LLM - Xlsum JA Rouge1 | 28.79 | Score (%) | 73.8 |
| Open Japanese LLM - Wiki Reading Char F1 | 80.35 | Score (%) | 73.3 |
| pfgen-bench - Completion Mode - Helpfulness | 0.26 | Helpfulness Score | 72.8 |
| Open Japanese LLM - Wiki NER SET F1 | 8.85 | Score (%) | 72 |
| pfgen-bench - Completion Mode - Score | 0.59 | pfgen Score (mean of three) | 71.9 |
| Open Japanese LLM - RC | 91.12 | Score (%) | 71.5 |
| Open Japanese LLM - SUM | 10.58 | Score (%) | 71.5 |
| Open Japanese LLM - Xlsum JA Rouge2 | 10.58 | Score (%) | 71.4 |
Interactive version: theaggregate.ai/model?slug=llama-3-elyza-jp-8b · How It Works · Data refreshed daily, snapshot 2026-11-08.