model_mergev2: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1548 ± 35, rank #1721 of 10916 rated models, from 50 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Japanese LLM - Wiki NER SET F1 | 15.93 | Score (%) | 96.9 |
| Open Japanese LLM - EL | 59.61 | Score (%) | 95 |
| Open Japanese LLM - Jsts Spearman | 87.86 | Score (%) | 90.3 |
| Open Japanese LLM - Jnli Exact Match | 88.17 | Score (%) | 87 |
| Open Japanese LLM - Jsem Exact Match | 79.86 | Score (%) | 83.5 |
| Open Japanese LLM - RC | 91.57 | Score (%) | 81.7 |
| Open Japanese LLM - Jsts Pearson | 90.05 | Score (%) | 81.1 |
| Open Japanese LLM - Jmmlu Exact Match | 72.32 | Score (%) | 80 |
| Open Japanese LLM - MMLU EN Exact Match | 77.96 | Score (%) | 80 |
| Open Japanese LLM - HE | 75.14 | Score (%) | 79.8 |
| Open Japanese LLM - Jamp Exact Match | 67.82 | Score (%) | 79.4 |
| Open Japanese LLM - Wikicorpus J TO E Comet Wmt22 | 75.87 | Score (%) | 76.4 |
Interactive version: theaggregate.ai/model?slug=model-mergev2 · How It Works · Data refreshed daily, snapshot 2026-11-08.