karakuri-lm-70B-chat-v0.1: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1439 ± 26, rank #4249 of 10916 rated models, from 64 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Japanese LLM - Xlsum JA RougeLsum | 27.59 | Score (%) | 90.9 |
| Open Japanese LLM - Xlsum JA Rouge1 | 32.72 | Score (%) | 90.4 |
| Open Japanese LLM - AIO Char F1 | 78.76 | Score (%) | 88.7 |
| Open Japanese LLM - SUM | 11.35 | Score (%) | 86.9 |
| Open Japanese LLM - Xlsum JA Rouge2 | 11.35 | Score (%) | 86.9 |
| Open Japanese LLM - Xlsum JA Bert Score JA F1 | 70.48 | Score (%) | 85.8 |
| Open Japanese LLM - QA | 62.36 | Score (%) | 85.6 |
| Open Japanese LLM - Niilc Char F1 | 56.56 | Score (%) | 83.4 |
| pfgen-bench - Completion Mode - Helpfulness | 0.31 | Helpfulness Score | 79.9 |
| Open Japanese LLM - Wikicorpus J TO E Bleu EN | 11.45 | Score (%) | 77.6 |
| pfgen-bench - Completion Mode - Score | 0.62 | pfgen Score (mean of three) | 75.7 |
| pfgen-bench - Completion Mode - Fluency | 0.71 | Fluency Score | 74 |
Interactive version: theaggregate.ai/model?slug=karakuri-lm-70b-chat-v0-1 · How It Works · Data refreshed daily, snapshot 2026-11-08.