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

BenchmarkScoreMetricPercentile
EuroEval Albanian NLU - MultiWikiQA SQ70.8Character F1 (%)100
EuroEval Bulgarian NLU - Cinexio64.59Matthews correlation coefficient (%)100
EuroEval Bulgarian NLU - MultiWikiQA BG81.84Character F1 (%)100
EuroEval Czech NLU - SQAD75.45Character F1 (%)100
EuroEval Dutch NLU - SQuAD NL86.49Character F1 (%)100
EuroEval German NLU - Germanquad72.66Character F1 (%)100
EuroEval Hungarian NLU - MultiWikiQA HU73.63Character F1 (%)100
EuroEval Icelandic NLU - NQII68.14Character F1 (%)100
EuroEval Latvian NLU - MultiWikiQA LV73.45Character F1 (%)100
EuroEval Lithuanian NLU - MultiWikiQA LT77.79Character F1 (%)100
EuroEval Faroese NLU - FoQA80.83Character F1 (%)99.7
EuroEval French NLU - FQuAD77.76Character F1 (%)99.7

Interactive version: theaggregate.ai/model?slug=qwen3-5-9b-base · How It Works · Data refreshed daily, snapshot 2026-11-08.