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 1525 ± 36, rank #702 of 1776 rated models, from 39 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA TAU-2 Bench | 87.72 | Accuracy (%) | 81.8 |
| AA GPQA Diamond | 71.21 | Accuracy (%) | 54.7 |
| AA Humanity's Last Exam | 7.46 | Accuracy (%) | 53.2 |
| Artificial Analysis Intelligence Index | 16 | Intelligence Index | 51.1 |
| AA-LCR | 28.3 | Score (self-reported) | 47.9 |
| AA Terminal-Bench Hard | 11.36 | Accuracy (%) | 46.8 |
| AA Long Context Reasoning | 28.33 | Accuracy (%) | 39.5 |
| AA MMMU-Pro | 62.08 | Accuracy (%) | 37.5 |
| AA Omniscience - Software Engineering (SWE) - Julia | 8 | Accuracy (%) | 37.3 |
| UGI - Writing | 29.68 | Writing Score | 35.8 |
| AA Omniscience - Software Engineering (SWE) - JavaScript | 24.55 | Accuracy (%) | 33.9 |
| AA Omniscience - Software Engineering (SWE) - Dart | 16 | Accuracy (%) | 33.7 |
Interactive version: theaggregate.ai/model?slug=qwen-3-5-4b-non-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.