Qwen 3 30B A3B (Non-reasoning): benchmark results
Qwen 3 30B A3B evaluated with reasoning disabled. Provider: Alibaba. Released 2025-04-29. Access: Open.
Aggregate Rating 1507 ± 13, rank #1051 of 2168 rated models, from 234 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Spanish NLU - Sentiment Headlines ES | 51.72 | Matthews correlation coefficient (%) | 94.9 |
| EuroEval Czech | 58.64 | Average Score (%) | 89.9 |
| EuroEval Spanish | 59.15 | Average Score (%) | 89.8 |
| EuroEval Dutch | 70.03 | Average Score (%) | 89.1 |
| EuroEval Spanish NLU | 55.25 | NLU Average Score (%) | 88.5 |
| EuroEval Portuguese | 63.05 | Average Score (%) | 87.6 |
| EuroEval Portuguese NLU - MultiWikiQA PT | 75.63 | Character F1 (%) | 87.3 |
| EuroEval Estonian NLU - Estonian Valence | 60.24 | Matthews correlation coefficient (%) | 87.2 |
| EuroEval English | 73.58 | Average Score (%) | 87 |
| EuroEval Latvian NLU - Latvian Twitter Sentiment | 49.75 | Matthews correlation coefficient (%) | 86.6 |
| EuroEval Lithuanian NLU | 52.81 | NLU Average Score (%) | 86.5 |
| EuroEval Italian | 61.23 | Average Score (%) | 86.4 |
Interactive version: theaggregate.ai/model?slug=qwen-3-30b-a3b-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-10-20.