Phos-7B: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1455 ± 36, rank #3547 of 10916 rated models, from 50 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Japanese LLM - Xlsum JA RougeLsum | 24.97 | Score (%) | 77.2 |
| Open Japanese LLM - Xlsum JA Rouge1 | 29.03 | Score (%) | 75.2 |
| Open Japanese LLM - Xlsum JA Rouge2 | 10.67 | Score (%) | 74.5 |
| Open Japanese LLM - SUM | 10.67 | Score (%) | 74.3 |
| Open Japanese LLM - Xlsum JA Bert Score JA F1 | 69.77 | Score (%) | 70.7 |
| Open Japanese LLM - Xlsum JA Bleu JA | 2.53 | Score (%) | 44.8 |
| Open Japanese LLM - AIO Char F1 | 51.21 | Score (%) | 44.5 |
| Open Japanese LLM - ALT E TO J Comet Wmt22 | 89.44 | Score (%) | 41.6 |
| Open Japanese LLM - Jamp Exact Match | 55.17 | Score (%) | 38.5 |
| Open Japanese LLM - Commonsensemoralja Exact Match | 84.64 | Score (%) | 37 |
| Open Japanese LLM - Mbpp Pylint Check | 6.63 | Score (%) | 36.5 |
| Open Japanese LLM - Wikicorpus E TO J Comet Wmt22 | 79.17 | Score (%) | 35.8 |
Interactive version: theaggregate.ai/model?slug=phos-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.