Qwen 3 32B (Non-reasoning): benchmark results
Provider: Alibaba. Released 2025-04-29. Access: Open.
Unified ELO 1526 ± 1, rank #1154 of 3078 rated models, from 311 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Romanian NLU | 68.83 | NLU Average Score (%) | 99.5 |
| EuroEval Norwegian NLU - Norquad | 78.03 | Reading comprehension Score (%) | 99 |
| EuroEval Hungarian NLU - MultiWikiQA HU | 70.37 | Reading comprehension Score (%) | 98.5 |
| EuroEval Portuguese NLU - MultiWikiQA PT | 79.03 | Reading comprehension Score (%) | 98.2 |
| EuroEval Catalan NLU | 66.7 | NLU Average Score (%) | 98.1 |
| EuroEval English NLU - SQuAD | 89.16 | Reading comprehension Score (%) | 97.9 |
| EuroEval Spanish NLU - Sentiment Headlines ES | 52.82 | Sentiment classification Score (%) | 97.6 |
| EuroEval Catalan NLU - ScaLA CA | 63.84 | Linguistic acceptability Score (%) | 97.2 |
| EuroEval Danish NLU - Multi Wiki QA DA | 81.7 | Reading comprehension Score (%) | 97 |
| EuroEval French NLU - FQuAD | 75.96 | Reading comprehension Score (%) | 96.8 |
| EuroEval Romanian NLU - MultiWikiQA RO | 75.86 | Reading comprehension Score (%) | 96.6 |
| EuroEval Albanian NLU - MultiWikiQA SQ | 67.72 | Reading comprehension Score (%) | 96.5 |
Interactive version: theaggregate.ai/model?slug=qwen-3-32b-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-19.