Linkbricks-Horizon-AI-Llama-3.3-Japanese-70B-Advanced: benchmark results
Provider: Linkbricks Horizon-AI. Access: Open.
Aggregate Rating 1517 ± 35, rank #2096 of 10916 rated models, from 50 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Japanese LLM - Xlsum JA Bleu JA | 3.36 | Score (%) | 89.5 |
| Open Japanese LLM - Wikicorpus E TO J Bleu JA | 14.71 | Score (%) | 88.2 |
| Open Japanese LLM - ALT E TO J Bert Score JA F1 | 86.84 | Score (%) | 86.8 |
| Open Japanese LLM - MMLU EN Exact Match | 79.88 | Score (%) | 86.5 |
| Open Japanese LLM - MR | 93.6 | Score (%) | 85.8 |
| Open Japanese LLM - Wikicorpus J TO E Bleu EN | 11.81 | Score (%) | 85.1 |
| Open Japanese LLM - QA | 61.55 | Score (%) | 84.4 |
| Open Japanese LLM - ALT J TO E Bleu EN | 17.85 | Score (%) | 84.3 |
| Open Japanese LLM - Jemhopqa Char F1 | 59.82 | Score (%) | 83.2 |
| Open Japanese LLM - AIO Char F1 | 69.9 | Score (%) | 82.5 |
| Open Japanese LLM - ALT E TO J Bleu JA | 13.35 | Score (%) | 82.2 |
| Open Japanese LLM - ALT J TO E Bert Score EN F1 | 95.55 | Score (%) | 81.7 |
Interactive version: theaggregate.ai/model?slug=linkbricks-horizon-ai-llama-3-3-japanese-70b-advanced · How It Works · Data refreshed daily, snapshot 2026-11-08.