Llama3.1-ArrowSE-v0.4: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1492 ± 35, rank #2483 of 10916 rated models, from 50 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Japanese LLM - Wiki Reading Char F1 | 81.55 | Score (%) | 77.3 |
| Open Japanese LLM - AIO Char F1 | 59.02 | Score (%) | 72.8 |
| Open Japanese LLM - Xlsum JA Bert Score JA F1 | 69.64 | Score (%) | 66.1 |
| Open Japanese LLM - SUM | 10.12 | Score (%) | 61.3 |
| Open Japanese LLM - Xlsum JA Rouge2 | 10.13 | Score (%) | 61.3 |
| Open Japanese LLM - Xlsum JA RougeLsum | 22.97 | Score (%) | 61.2 |
| Open Japanese LLM - Wiki NER SET F1 | 6.19 | Score (%) | 57.2 |
| Open Japanese LLM - Xlsum JA Bleu JA | 2.69 | Score (%) | 55 |
| Open Japanese LLM - Xlsum JA Rouge1 | 26.25 | Score (%) | 54.8 |
| Open Japanese LLM - QA | 53.14 | Score (%) | 53.4 |
| Open Japanese LLM - RC | 90.31 | Score (%) | 50.1 |
| Open Japanese LLM - Jemhopqa Char F1 | 52.58 | Score (%) | 49.9 |
Interactive version: theaggregate.ai/model?slug=llama3-1-arrowse-v0-4 · How It Works · Data refreshed daily, snapshot 2026-11-08.