ReasonFlux-F1: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1541 ± 35, rank #1826 of 10916 rated models, from 50 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Japanese LLM - Wiki NER SET F1 | 14.16 | Score (%) | 93.1 |
| Open Japanese LLM - Xlsum JA Rouge1 | 30.96 | Score (%) | 86.1 |
| Open Japanese LLM - EL | 58.01 | Score (%) | 83.7 |
| Open Japanese LLM - Jmmlu Exact Match | 72.44 | Score (%) | 81.6 |
| Open Japanese LLM - Jsts Spearman | 87.53 | Score (%) | 79.2 |
| Open Japanese LLM - HE | 74.92 | Score (%) | 77.5 |
| Open Japanese LLM - Jsts Pearson | 89.87 | Score (%) | 76.6 |
| Open Japanese LLM - MMLU EN Exact Match | 77.4 | Score (%) | 74.8 |
| Open Japanese LLM - MR | 91.8 | Score (%) | 74 |
| Open Japanese LLM - Xlsum JA Rouge2 | 10.65 | Score (%) | 73.8 |
| Open Japanese LLM - Jamp Exact Match | 66.95 | Score (%) | 73.7 |
| Open Japanese LLM - SUM | 10.64 | Score (%) | 73.7 |
Interactive version: theaggregate.ai/model?slug=reasonflux-f1 · How It Works · Data refreshed daily, snapshot 2026-11-08.