llm-jp-3-7.2B-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 1527 ± 46, rank #1990 of 10916 rated models, from 19 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| pfgen-bench - Completion Mode - Helpfulness | 0.4 | Helpfulness Score | 90.1 |
| pfgen-bench - Completion Mode - Score | 0.7 | pfgen Score (mean of three) | 87.9 |
| pfgen-bench - Completion Mode - Fluency | 0.8 | Fluency Score | 86.9 |
| pfgen-bench - Completion Mode - Truthfulness | 0.9 | Truthfulness Score | 86.9 |
| pfgen-bench - QA Mode - Fluency | 0.77 | Fluency Score | 82.4 |
| pfgen-bench - QA Mode - Score | 0.67 | pfgen Score (mean of three) | 78.8 |
| pfgen-bench - QA Mode - Helpfulness | 0.36 | Helpfulness Score | 75.8 |
| pfgen-bench - Chat Mode - Fluency | 0.64 | Fluency Score | 73.5 |
| pfgen-bench - QA Mode - Truthfulness | 0.87 | Truthfulness Score | 71.2 |
| pfgen-bench - Chat Mode - Score | 0.55 | pfgen Score (mean of three) | 61.8 |
| pfgen-bench - Chat Mode - Truthfulness | 0.79 | Truthfulness Score | 61.8 |
| pfgen-bench - Chat Mode - Helpfulness | 0.23 | Helpfulness Score | 52.9 |
Interactive version: theaggregate.ai/model?slug=llm-jp-3-7-2b-instruct3 · How It Works · Data refreshed daily, snapshot 2026-11-08.