Qwen 3.5 4B (Non-reasoning): benchmark results
Qwen 3.5 4B evaluated with reasoning disabled. Provider: Alibaba. Released 2026-03-01. Access: Open.
Unified ELO 1494 ± 1, rank #892 of 1761 rated models, from 37 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA TAU-2 Bench | 87.72 | Accuracy (%) | 81.9 |
| AA Omniscience - Software Engineering (SWE) - Dart | 18 | Accuracy (%) | 51.5 |
| AA GPQA Diamond | 71.21 | Accuracy (%) | 50 |
| AA Humanity's Last Exam | 7.97 | Accuracy (%) | 48.9 |
| Artificial Analysis Intelligence Index | 10.02 | Intelligence Index | 47.3 |
| AA Terminal-Bench Hard | 11.36 | Accuracy (%) | 46.8 |
| AA Omniscience - Software Engineering (SWE) - Julia | 8 | Accuracy (%) | 46.1 |
| AA Omniscience - Software Engineering (SWE) - JavaScript | 25.45 | Accuracy (%) | 42 |
| OTIS Mock AIME 2024-25 | 55.83 | Accuracy (%) | 42 |
| AA Omniscience - Software Engineering (SWE) - R | 6 | Accuracy (%) | 36.2 |
| AA Long Context Reasoning | 34.67 | Accuracy (%) | 35.7 |
| UGI - Writing | 29.68 | Writing Score | 35.4 |
Interactive version: theaggregate.ai/model?slug=qwen-3-5-4b-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-05.