Alibaba Cloud / Qwen Team
qwen3.5-27b
apache_2_0Multimodal
Benchmark Average (0–100)
71.4%
Average of non-null benchmark scores across all evaluated tasks.
BENCHMARK SCORES
GPQA85.5%
Graduate-Level Google-Proof Q&A. PhD-level multiple-choice questions in chemistry, biology, and physics. Scored by accuracy.
SWE-bench Verified72.4%
SWE-bench Verified evaluates models on real-world software engineering tasks from GitHub issues.
MMMLU85.9%
Multilingual MMLU tests knowledge across many languages and subject areas.
BrowseComp61.0%
BrowseComp tests web browsing comprehension, measuring ability to find and synthesize information from websites.
HLE48.5%
Humanity's Last Exam (HLE) is a multi-modal benchmark testing frontier knowledge across mathematics, humanities, and natural sciences with 2,500 expert-level questions.
MMMU-Pro75.0%
MMMU-Pro is a more challenging version of MMMU with harder multimodal understanding tasks.
OTHER BENCHMARKS
MMMU
82.3%
CharXIV-R
79.5%
ScreenSpot Pro
70.3%
MODEL INFO
Organization
Alibaba Cloud / Qwen Team
Context Window
—
Release Date
2026-02-24
Knowledge Cutoff
—
Parameters
27000000000.0B
License
apache_2_0
METADATA
Announcement Date
2026-02-24
Organization Country
CN
Canonical ID
—