Llama3.1-Swallow-8B: benchmark results
Provider: Meta.
Aggregate Rating 1605 ± 46, rank #968 of 10916 rated models, from 2 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Benchmarking Large Language Models for Graphem | 22.47 | Direct (self-reported) | 50 |
| Japanese G2P (Parse Mode) | 9.34 | Kana character error rate (%; can exceed 100) in parse mode | 44.4 |
Interactive version: theaggregate.ai/model?slug=llama3-1-swallow-8b · How It Works · Data refreshed daily, snapshot 2026-11-08.