Qwen 3 1.7B (Non-reasoning): benchmark results
Qwen 3 1.7B evaluated with reasoning disabled. Provider: Alibaba. Released 2025-04-29. Access: Open.
Aggregate Rating 1334 ± 11, rank #1732 of 2170 rated models, from 327 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Ukrainian Summarization - LR SUM UK | 30.85 | chrF3++ (%) | 89 |
| EuroEval Catalan Summarization - Dacsa CA | 38.15 | chrF3++ (%) | 88.3 |
| EuroEval Italian NLU - ScaLA IT | 42.53 | Matthews correlation coefficient (%) | 88 |
| EuroEval Polish Summarization - PSC | 24.52 | chrF3++ (%) | 87.1 |
| EuroEval Bosnian Summarization - LR SUM BS | 30.79 | chrF3++ (%) | 86.3 |
| EuroEval French NLU - ScaLA FR | 49.2 | Matthews correlation coefficient (%) | 86.2 |
| EuroEval Serbian Summarization - LR SUM SR | 30.1 | chrF3++ (%) | 84.4 |
| EuroEval Portuguese NLU - ScaLA PT | 29.31 | Matthews correlation coefficient (%) | 84.1 |
| EuroEval Dutch Summarization - Wiki Lingua NL | 34.18 | chrF3++ (%) | 80.7 |
| EuroEval English Summarization - CNN Dailymail | 42.72 | chrF3++ (%) | 78 |
| EuroEval Albanian Summarization - LR SUM SQ | 32.34 | chrF3++ (%) | 72.5 |
| EuroEval Swedish Summarization - Swedn | 36.88 | chrF3++ (%) | 71.4 |
Interactive version: theaggregate.ai/model?slug=qwen-3-1-7b-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-05.