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 1607 ± 25, rank #465 of 1776 rated models, from 56 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA TAU-2 Bench | 86.26 | Accuracy (%) | 78.9 |
| AA GPQA Diamond | 81.92 | Accuracy (%) | 76.1 |
| AA Humanity's Last Exam | 12.79 | Accuracy (%) | 69.9 |
| AA Global-MMLU-Lite - Yoruba | 63.58 | Accuracy (%) | 67.6 |
| Artificial Analysis Intelligence Index | 23.99 | Intelligence Index | 66.8 |
| AA CritPt | 0.57 | Accuracy (%) | 64.9 |
| AA Long Context Reasoning | 55.33 | Accuracy (%) | 64.6 |
| UGI - Writing | 37 | Writing Score | 62.4 |
| UGI - Natural Intelligence | 24.97 | NatInt Score | 62.2 |
| AA Global-MMLU-Lite - Spanish | 88.67 | Accuracy (%) | 59 |
| AA MMMU-Pro | 69.19 | Accuracy (%) | 56.4 |
| AA Global-MMLU-Lite - Swahili | 75.33 | Accuracy (%) | 55.9 |
Interactive version: theaggregate.ai/model?slug=qwen-3-5-35b-a3b-non-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.