karakuri-lm-8x7B-instruct-v0.1: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1498 ± 30, rank #2380 of 10916 rated models, from 58 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Japanese LLM - Xlsum JA Rouge2 | 11.5 | Score (%) | 89.2 |
| Open Japanese LLM - SUM | 11.5 | Score (%) | 89.1 |
| Open Japanese LLM - Wiki NER SET F1 | 12.39 | Score (%) | 87 |
| Open Japanese LLM - Wiki PAS SET F1 | 9.08 | Score (%) | 86.8 |
| Open Japanese LLM - Xlsum JA RougeLsum | 25.7 | Score (%) | 83.9 |
| Open Japanese LLM - Xlsum JA Rouge1 | 30.45 | Score (%) | 83.4 |
| pfgen-bench - Completion Mode - Fluency | 0.76 | Fluency Score | 82.4 |
| Open Japanese LLM - QA | 59.6 | Score (%) | 82.3 |
| Open Japanese LLM - AIO Char F1 | 69.05 | Score (%) | 81.2 |
| pfgen-bench - Completion Mode - Score | 0.64 | pfgen Score (mean of three) | 80.2 |
| Open Japanese LLM - Niilc Char F1 | 55.2 | Score (%) | 80 |
| pfgen-bench - Completion Mode - Truthfulness | 0.86 | Truthfulness Score | 78.4 |
Interactive version: theaggregate.ai/model?slug=karakuri-lm-8x7b-instruct-v0-1 · How It Works · Data refreshed daily, snapshot 2026-11-08.