Qwen 3.6 35B A3B Instruct: benchmark results
Provider: Alibaba. Released 2026-04-16.
Aggregate Rating 1684 ± 24, rank #424 of 10916 rated models, from 36 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Medmarks - MedCalc-Bench | 82 | Score (%) | 98.9 |
| LUNAR - RAG | 3.14 | Personalization score (1-5; mean of coverage and depth, GPT- | 94.4 |
| Medmarks - MedHallu Medium | 75 | Score (%) | 94.3 |
| Medmarks - MedConceptsQA Easy | 99.37 | Score (%) | 92 |
| Medmarks - MedHallu Easy | 81.21 | Score (%) | 92 |
| Medmarks - SuperGPQA Medicine Hard | 53.76 | Score (%) | 92 |
| LUNAR - Curated Context | 4.02 | Personalization score (1-5; mean of coverage and depth, GPT- | 91.7 |
| Medmarks - PubMedQA | 79.13 | Score (%) | 89.8 |
| LUNAR - Full Context | 3.63 | Personalization score (1-5; mean of coverage and depth, GPT- | 88.9 |
| Medmarks - MedHallu Hard | 55.4 | Score (%) | 87.5 |
| Medmarks - CareQA EN | 92.21 | Score (%) | 85.2 |
| Medmarks - MedQA | 92.62 | Score (%) | 85.2 |
Interactive version: theaggregate.ai/model?slug=qwen-3-6-35b-a3b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.