Qwen3.6-27B
Qwen3.6-27B 于2026年4月22日发布，是首个在全主要代码智能体评测上超越 Qwen3.5-397B-A17B 的开源稠密27B模型。SWE-bench Verified 77.2、Terminal Bench 2.0 59.3、SkillsBench 48.2（前代30.0）、AIME 2026 94.1（全球第4）。
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Model basics
Open source & experience
Official resources
API details
Benchmark Results
Qwen3.6-27B currently shows benchmark results led by MMLU Pro (16 / 126, score 86.20), LiveCodeBench (19 / 120, score 83.90), GPQA Diamond (33 / 178, score 87.80). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.
General Knowledge
4 evaluationsCoding and Software Engineer
4 evaluationsMath and Reasoning
2 evaluationsCompare with other models
- Earlier versionQwen3.6-27B vs Qwen3.5-27B8 benchmarks
- Peer modelQwen3.6-27B vs Haiku 4.57 benchmarks
- Peer modelQwen3.6-27B vs Gemini 3.0 Flash6 benchmarks
- Peer modelQwen3.6-27B vs GPT-5.4 mini5 benchmarks
- Earlier versionQwen3.6-27B vs Qwen3-32B3 benchmarks
Want a custom combination? Open the compare tool
Publisher
Model Overview
Qwen3.6-27B 于2026年4月22日发布，是首个在全主要代码智能体评测上超越 Qwen3.5-397B-A17B 的开源稠密27B模型。SWE-bench Verified 77.2、Terminal Bench 2.0 59.3、SkillsBench 48.2（前代30.0）、AIME 2026 94.1（全球第4）。
DataLearner on WeChat
Follow DataLearner on WeChat for AI model updates and research notes.
