Qwen 3.5 9B (Non-reasoning): benchmark results
Qwen 3.5 9B evaluated with reasoning disabled. Provider: Alibaba. Released 2026-03-02. Access: Open.
Unified ELO 1542 ± 1, rank #662 of 1761 rated models, from 39 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| CritPt | 60 | Accuracy (self-reported) | 91.9 |
| AA TAU-2 Bench | 85.09 | Accuracy (%) | 77.4 |
| AA GPQA Diamond | 78.59 | Accuracy (%) | 64.7 |
| AA CritPt | 0.57 | Accuracy (%) | 59 |
| AA Terminal-Bench Hard | 18.18 | Accuracy (%) | 57.3 |
| Artificial Analysis Intelligence Index | 14.13 | Intelligence Index | 56.4 |
| AA Omniscience - Software Engineering (SWE) - C | 32 | Accuracy (%) | 52.9 |
| AA Humanity's Last Exam | 9.36 | Accuracy (%) | 52.1 |
| UGI - Writing | 33.52 | Writing Score | 49.6 |
| AA Omniscience - Software Engineering (SWE) - Go | 16 | Accuracy (%) | 48.6 |
| OTIS Mock AIME 2024-25 | 61.67 | Accuracy (%) | 46.2 |
| AA MMMU-Pro | 66.76 | Accuracy (%) | 45.3 |
Interactive version: theaggregate.ai/model?slug=qwen-3-5-9b-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-05.