Llama-3.1-SuperSwallow-70B-Instruct-v0.1: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1583 ± 37, rank #1216 of 10916 rated models, from 50 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Japanese LLM - ALT E TO J Comet Wmt22 | 91.87 | Score (%) | 100 |
| Open Japanese LLM - Commonsensemoralja Exact Match | 93.96 | Score (%) | 100 |
| Open Japanese LLM - MT | 86.4 | Score (%) | 100 |
| Open Japanese LLM - Wikicorpus E TO J Comet Wmt22 | 86.8 | Score (%) | 99.8 |
| Open Japanese LLM - ALT E TO J Bert Score JA F1 | 88.05 | Score (%) | 99.5 |
| Open Japanese LLM - Wikicorpus E TO J Bert Score JA F1 | 87.02 | Score (%) | 99.5 |
| Open Japanese LLM - Xlsum JA Bert Score JA F1 | 78.78 | Score (%) | 99.3 |
| Open Japanese LLM - Xlsum JA Rouge1 | 52.57 | Score (%) | 99.3 |
| Open Japanese LLM - ALT E TO J Bleu JA | 15.47 | Score (%) | 99 |
| Open Japanese LLM - SUM | 28.01 | Score (%) | 99 |
| Open Japanese LLM - Wikicorpus E TO J Bleu JA | 18.16 | Score (%) | 99 |
| Open Japanese LLM - Wikicorpus J TO E Comet Wmt22 | 77.68 | Score (%) | 99 |
Interactive version: theaggregate.ai/model?slug=llama-3-1-superswallow-70b-instruct-v0-1 · How It Works · Data refreshed daily, snapshot 2026-11-08.