Qwen3.5-9B-Base: benchmark results
Provider: Alibaba. Released 2026-03-02. Access: Open.
Aggregate Rating 1531 ± 26, rank #1943 of 10916 rated models, from 281 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Albanian NLU - MultiWikiQA SQ | 70.8 | Character F1 (%) | 100 |
| EuroEval Bulgarian NLU - Cinexio | 64.59 | Matthews correlation coefficient (%) | 100 |
| EuroEval Bulgarian NLU - MultiWikiQA BG | 81.84 | Character F1 (%) | 100 |
| EuroEval Czech NLU - SQAD | 75.45 | Character F1 (%) | 100 |
| EuroEval Dutch NLU - SQuAD NL | 86.49 | Character F1 (%) | 100 |
| EuroEval German NLU - Germanquad | 72.66 | Character F1 (%) | 100 |
| EuroEval Hungarian NLU - MultiWikiQA HU | 73.63 | Character F1 (%) | 100 |
| EuroEval Icelandic NLU - NQII | 68.14 | Character F1 (%) | 100 |
| EuroEval Latvian NLU - MultiWikiQA LV | 73.45 | Character F1 (%) | 100 |
| EuroEval Lithuanian NLU - MultiWikiQA LT | 77.79 | Character F1 (%) | 100 |
| EuroEval Faroese NLU - FoQA | 80.83 | Character F1 (%) | 99.7 |
| EuroEval French NLU - FQuAD | 77.76 | Character F1 (%) | 99.7 |
Interactive version: theaggregate.ai/model?slug=qwen3-5-9b-base · How It Works · Data refreshed daily, snapshot 2026-11-08.