llm-jp-3-3.7B-instruct3: benchmark results
LLM-jp 3 instruction-tuned release developed by NII's LLM-jp project, using Llama architecture and a 4,096-token context window. The named instruction-tuning generation remains distinct from the pretrained checkpoint and other instruct generations. Provider: National Institute of Informatics. Access: Open.
Aggregate Rating 1415 ± 52, rank #5545 of 10556 rated models, from 58 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Japanese LLM - AIO Char F1 | 67.44 | Score (%) | 80.3 |
| Open Japanese LLM - Xlsum JA Rouge1 | 29.26 | Score (%) | 77.2 |
| Open Japanese LLM - Xlsum JA RougeLsum | 24.65 | Score (%) | 74.4 |
| pfgen-bench - QA Mode - Fluency | 0.7 | Fluency Score | 71.5 |
| pfgen-bench - QA Mode - Score | 0.61 | pfgen Score (mean of three) | 68.5 |
| pfgen-bench - QA Mode - Helpfulness | 0.3 | Helpfulness Score | 67.9 |
| pfgen-bench - QA Mode - Truthfulness | 0.83 | Truthfulness Score | 66.4 |
| Open Japanese LLM - Xlsum JA Bert Score JA F1 | 69.54 | Score (%) | 63.2 |
| Open Japanese LLM - SUM | 10.08 | Score (%) | 60.1 |
| Open Japanese LLM - Xlsum JA Rouge2 | 10.07 | Score (%) | 59.9 |
| Open Japanese LLM - Wiki Reading Char F1 | 77.26 | Score (%) | 56.2 |
| Open Japanese LLM - QA | 52.87 | Score (%) | 51.4 |
Interactive version: theaggregate.ai/model?slug=llm-jp-3-3-7b-instruct3 · How It Works · Data refreshed daily, snapshot 2026-11-17.