Qwen 3.6 35B A3B (Non-reasoning) — benchmark results
Qwen 3.6 35B A3B evaluated with reasoning disabled. Provider: Alibaba. Released 2026-04-16. Access: Open.
Unified ELO 1528 ± 54, rank #690 of 1776 rated models, from 39 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA TAU-2 Bench | 85.09 | Accuracy (%) | 77.4 |
| AA GPQA Diamond | 81.72 | Accuracy (%) | 75.9 |
| AA Humanity's Last Exam | 12.51 | Accuracy (%) | 69 |
| Artificial Analysis Intelligence Index | 24.16 | Intelligence Index | 67.2 |
| AA Terminal-Bench Hard | 25.76 | Accuracy (%) | 67.1 |
| AA Long Context Reasoning | 56.67 | Accuracy (%) | 67 |
| UGI - Natural Intelligence | 25.43 | NatInt Score | 63.9 |
| AA MMMU-Pro | 71.04 | Accuracy (%) | 63.2 |
| AA Omniscience - Software Engineering (SWE) - TypeScript | 27.78 | Accuracy (%) | 59.6 |
| AA Omniscience - Software Engineering (SWE) - Rust | 54 | Accuracy (%) | 59.5 |
| UGI - Writing | 35.83 | Writing Score | 58.6 |
| AA GDPval | 1020.43 | ELO | 57.3 |
Interactive version: theaggregate.ai/model?slug=qwen-3-6-35b-a3b-non-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.