Qwen 3.6 35B A3B (Reasoning): benchmark results
Provider: Alibaba. Released 2026-04-16. Access: Open.
Unified ELO 1606 ± 1, rank #406 of 1761 rated models, from 37 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA TAU-2 Bench | 95.32 | Accuracy (%) | 94.5 |
| CritPt | 30 | Accuracy (self-reported) | 80.8 |
| AA Terminal-Bench Hard | 34.85 | Accuracy (%) | 80.3 |
| AA IFBench | 64.35 | Accuracy (%) | 75.4 |
| AA GPQA Diamond | 84.14 | Accuracy (%) | 75 |
| AA Humanity's Last Exam | 22.24 | Accuracy (%) | 74.7 |
| AA Omniscience - Software Engineering (SWE) - JavaScript | 36.36 | Accuracy (%) | 74.6 |
| Artificial Analysis Intelligence Index | 26.21 | Intelligence Index | 74.4 |
| AA Omniscience - Software Engineering (SWE) - Rust | 56 | Accuracy (%) | 74.1 |
| AA Omniscience - Software Engineering (SWE) - C | 43 | Accuracy (%) | 70.8 |
| AA Long Context Reasoning | 71.67 | Accuracy (%) | 70.7 |
| AA MMMU-Pro | 75.03 | Accuracy (%) | 70.3 |
Interactive version: theaggregate.ai/model?slug=qwen-3-6-35b-a3b-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-05.