Llama 3.1 70B EZO 1.1 IT: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1576 ± 33, rank #1306 of 10916 rated models, from 54 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Japanese LLM - Commonsensemoralja Exact Match | 93.54 | Score (%) | 98.9 |
| Open Japanese LLM - MC | 90.71 | Score (%) | 94.4 |
| Open Japanese LLM - Jsem Exact Match | 80.56 | Score (%) | 93.8 |
| Open Japanese LLM - Niilc Char F1 | 65.16 | Score (%) | 93.8 |
| Open Japanese LLM - QA | 70.38 | Score (%) | 93.3 |
| Open Japanese LLM - AIO Char F1 | 84.29 | Score (%) | 92.8 |
| Open Japanese LLM - Jcommonsenseqa Exact Match | 96.07 | Score (%) | 92.3 |
| Open Japanese LLM - ALT E TO J Comet Wmt22 | 91.09 | Score (%) | 90.9 |
| Open Japanese LLM - Jemhopqa Char F1 | 61.68 | Score (%) | 88.8 |
| Open Japanese LLM - Wikicorpus E TO J Comet Wmt22 | 84.52 | Score (%) | 88.7 |
| Open Japanese LLM - Wikicorpus J TO E Comet Wmt22 | 76.38 | Score (%) | 88.1 |
| Open Japanese LLM - Wiki NER SET F1 | 12.39 | Score (%) | 87 |
Interactive version: theaggregate.ai/model?slug=llama-3-1-70b-ezo-1-1-it · How It Works · Data refreshed daily, snapshot 2026-11-08.