Qwen 3.6 27B: benchmark results
Alibaba's dense open Qwen 3.6 27B model, tuned for agentic coding. Provider: Alibaba. Released 2026-04-22. Access: Open.
Aggregate Rating 1716 ± 4, rank #164 of 1635 rated models, from 1207 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| CATTest - Pass/Not-Pass Precision | 89.06 | Precision (%) | 100 |
| CheXpercept | 92.2 | Stage 1 (End-to-End) (self-reported) | 100 |
| Claw-Anything - CLI and GUI Tasks | 18 | Pass@1 (%) on the 50 tasks that need both the CLI and the GU | 100 |
| Embodied-BenchClaw Aerial-Bench - Interval Selection | 44 | Accuracy (%) on interval selection questions (counts, quanti | 100 |
| FirmCORe - Opportunity Detection | 74.51 | Macro-F1 (%) | 100 |
| KIDBench (Implicit Cue) - Content Safety | 4.68 | Content Safety score (1-5): whether the response avoids harm | 100 |
| KIDBench (Implicit Cue) - Family, Peers, and Relationships | 4.74 | Category score (1-5): mean of the five child-safety dimensio | 100 |
| KIDBench (Implicit Cue) - School Conduct and Integrity | 4.15 | Category score (1-5): mean of the five child-safety dimensio | 100 |
| KIDBench (No Cue) - Content Safety | 4.16 | Content Safety score (1-5): whether the response avoids harm | 100 |
| KIDBench (No Cue) - Self-harm and Mental Health | 2.66 | Category score (1-5): mean of the five child-safety dimensio | 100 |
| KIDBench - Cultural Alignment (China) | 4.24 | Cultural Alignment score (1-5): whether the response adapts | 100 |
| KIDBench - Cultural Alignment (India) | 4.41 | Cultural Alignment score (1-5): whether the response adapts | 100 |
Interactive version: theaggregate.ai/model?slug=qwen-3-6-27b · How It Works · Data refreshed daily, snapshot 2026-10-15.