ReasonFlux-F1-7B: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1343 ± 37, rank #7896 of 10916 rated models, from 50 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Japanese LLM - Wiki NER SET F1 | 3.54 | Score (%) | 39.4 |
| Open Japanese LLM - MR | 71.2 | Score (%) | 32.9 |
| Open Japanese LLM - CG | 0.2 | Score (%) | 27.6 |
| Open Japanese LLM - Wiki Coreference SET F1 | 1.15 | Score (%) | 26.8 |
| Open Japanese LLM - Jsem Exact Match | 69.19 | Score (%) | 22.8 |
| Open Japanese LLM - Mbpp Pylint Check | 0.2 | Score (%) | 21.8 |
| Open Japanese LLM - Janli Exact Match | 59.44 | Score (%) | 21.2 |
| Open Japanese LLM - Jmmlu Exact Match | 40.84 | Score (%) | 19.6 |
| Open Japanese LLM - NLI | 55.58 | Score (%) | 19.5 |
| Open Japanese LLM - Jsts Pearson | 68.45 | Score (%) | 18.8 |
| Open Japanese LLM - Jsts Spearman | 61.84 | Score (%) | 18.5 |
| Open Japanese LLM - Kuci Exact Match | 43.25 | Score (%) | 18 |
Interactive version: theaggregate.ai/model?slug=reasonflux-f1-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.