Llama-3.3-SuperSwallow-70B-Instruct-v0.1: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1563 ± 37, rank #1506 of 10916 rated models, from 50 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Japanese LLM - Commonsensemoralja Exact Match | 93.11 | Score (%) | 96.6 |
| Open Japanese LLM - Jsem Exact Match | 80.87 | Score (%) | 96.4 |
| Open Japanese LLM - AIO Char F1 | 86.05 | Score (%) | 96 |
| Open Japanese LLM - ALT E TO J Comet Wmt22 | 91.36 | Score (%) | 95.9 |
| Open Japanese LLM - Janli Exact Match | 91.53 | Score (%) | 95.9 |
| Open Japanese LLM - ALT E TO J Bert Score JA F1 | 87.34 | Score (%) | 95.6 |
| Open Japanese LLM - MC | 90.85 | Score (%) | 95.2 |
| Open Japanese LLM - Niilc Char F1 | 65.97 | Score (%) | 95.1 |
| Open Japanese LLM - Wikicorpus E TO J Comet Wmt22 | 85.29 | Score (%) | 94.8 |
| Open Japanese LLM - QA | 70.76 | Score (%) | 94.5 |
| Open Japanese LLM - EL | 59.26 | Score (%) | 93.8 |
| Open Japanese LLM - Kuci Exact Match | 84.18 | Score (%) | 93.5 |
Interactive version: theaggregate.ai/model?slug=llama-3-3-superswallow-70b-instruct-v0-1 · How It Works · Data refreshed daily, snapshot 2026-11-08.