YuLan-Mini-Instruct: benchmark results
Provider: YuLan. Released 2025-02-21. Access: Open.
Aggregate Rating 1297 ± 28, rank #8781 of 10916 rated models, from 264 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval English Summarization - CNN Dailymail | 42.69 | chrF3++ (%) | 76.7 |
| EuroEval Serbian Summarization - LR SUM SR | 28.18 | chrF3++ (%) | 66 |
| EuroEval Spanish Summarization - Mlsum ES | 26.15 | chrF3++ (%) | 64.6 |
| EuroEval Portuguese Summarization - Publico | 31.75 | chrF3++ (%) | 57.4 |
| EuroEval Catalan Summarization - Dacsa CA | 33.85 | chrF3++ (%) | 56.5 |
| EuroEval Albanian Summarization - LR SUM SQ | 29.61 | chrF3++ (%) | 55.2 |
| EuroEval Bosnian Summarization - LR SUM BS | 27.49 | chrF3++ (%) | 54.6 |
| EuroEval Faroese NLU - ScaLA FO | 3.52 | Matthews correlation coefficient (%) | 52.8 |
| EuroEval French Summarization - Orange SUM | 35.25 | chrF3++ (%) | 50 |
| EuroEval Catalan NLU - ScaLA CA | 4.55 | Matthews correlation coefficient (%) | 48.8 |
| EuroEval English NLU - SST-5 | 64.47 | Matthews correlation coefficient (%) | 48.2 |
| EuroEval Estonian Summarization - ERR News | 26.86 | chrF3++ (%) | 47.7 |
Interactive version: theaggregate.ai/model?slug=yulan-mini-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.