Llama-3.1-Swallow-8B-v0.2: benchmark results
Provider: Institute of Science Tokyo. Released 2024-11-11. Access: Open.
Aggregate Rating 1507 ± 37, rank #2238 of 10916 rated models, from 54 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Japanese LLM - ALT E TO J Bert Score JA F1 | 87.47 | Score (%) | 96.9 |
| pfgen-bench - Completion Mode - Fluency | 0.82 | Fluency Score | 91.5 |
| Open Japanese LLM - Niilc Char F1 | 62.76 | Score (%) | 90.9 |
| Open Japanese LLM - ALT E TO J Bleu JA | 13.86 | Score (%) | 89.7 |
| Open Japanese LLM - AIO Char F1 | 80.15 | Score (%) | 89.2 |
| pfgen-bench - Completion Mode - Score | 0.7 | pfgen Score (mean of three) | 89.1 |
| pfgen-bench - Completion Mode - Truthfulness | 0.9 | Truthfulness Score | 88.7 |
| Open Japanese LLM - Wiki Reading Char F1 | 86.58 | Score (%) | 88.5 |
| pfgen-bench - Completion Mode - Helpfulness | 0.39 | Helpfulness Score | 88.2 |
| Open Japanese LLM - ALT E TO J Comet Wmt22 | 90.99 | Score (%) | 87.5 |
| Open Japanese LLM - Wikicorpus J TO E Bleu EN | 12.14 | Score (%) | 87.3 |
| Open Japanese LLM - Wikicorpus J TO E Bert Score EN F1 | 90.93 | Score (%) | 87.1 |
Interactive version: theaggregate.ai/model?slug=llama-3-1-swallow-8b-v0-2 · How It Works · Data refreshed daily, snapshot 2026-11-08.