Qwen 3.5 35B A3B (Non-reasoning): benchmark results
Qwen 3.5 35B A3B evaluated with reasoning disabled. Provider: Alibaba. Released 2026-02-24. Access: Open.
Unified ELO 1562 ± 1, rank #593 of 1761 rated models, from 59 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| CritPt | 60 | Accuracy (self-reported) | 91.9 |
| AA TAU-2 Bench | 86.26 | Accuracy (%) | 78.9 |
| AA GPQA Diamond | 81.92 | Accuracy (%) | 70.1 |
| AA Global-MMLU-Lite - Yoruba | 63.58 | Accuracy (%) | 67.6 |
| AA Humanity's Last Exam | 13.44 | Accuracy (%) | 63.4 |
| UGI - Writing | 37 | Writing Score | 61.8 |
| Artificial Analysis Intelligence Index | 16.96 | Intelligence Index | 61.6 |
| UGI - Natural Intelligence | 24.97 | NatInt Score | 61.5 |
| AA Omniscience - Software Engineering (SWE) - Dart | 20 | Accuracy (%) | 59.4 |
| AA CritPt | 0.57 | Accuracy (%) | 59 |
| AA Omniscience - Software Engineering (SWE) - Rust | 50 | Accuracy (%) | 59 |
| AA Global-MMLU-Lite - Spanish | 88.67 | Accuracy (%) | 57.7 |
Interactive version: theaggregate.ai/model?slug=qwen-3-5-35b-a3b-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-05.