Qwen3.6 27B is a native vision-language dense model with stronger agentic coding and STEM reasoning than Qwen 3.5 27B. It also improves spatial intelligence (including object localization/detection), plus video understanding, document OCR, and visual-agent workflows.
Added Apr 23, 2026
Model weightsContext Window
260.1K
Max Output
65.5K
Avg output tokens (7d)
675 tokens
Input Price (Auto)
$0.30/1M
Output Price (Auto)
$2.00/1M
Cache Read (Auto)
$0.030/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
21.4
Coding Index
53.7
Agentic Index
18.5
Agentic work
AutomationBench-AA
Workflow automation with guardrail penalties
11.0%
Better than 34% of models compared
Harvey LAB-AA
Legal agentic work criterion pass rate
82.3%
Better than 29% of models compared
AA-Briefcase
Agentic knowledge work (Elo)
813 Elo
Better than 35% of models compared
GDPval-AA v2
Economically valuable tasks (Elo)
973 Elo
Better than 45% of models compared
Document reasoning
GDP.pdf
Professional PDF reasoning: all-pass rate
11.0%
Better than 43% of models compared
AA-LCR v1.1
Long context reasoning with updated grading
77.3%
Better than 78% of models compared
Reasoning
HLE
Humanity's Last Exam
23.1%
Better than 72% of models compared
IFBench
Instruction-following benchmark
67.6%
Better than 81% of models compared
Coding
Terminal-Bench v4.0
Practical coding and terminal tasks
0.0%
Better than 16% of models compared
SciCode
Python programming for scientific computing
42.8%
Better than 33% of models compared
Legacy benchmarks
GPQA Diamond (legacy)
Graduate-level scientific reasoning
84.2%
Better than 75% of models compared
Terminal-Bench Hard (legacy)
Agentic coding and terminal use
34.8%
Better than 80% of models compared
T²-Bench Telecom (legacy)
Conversational AI agents in dual-control scenarios
94.2%
Better than 92% of models compared
AA-LCR (unversioned / legacy)
Long context reasoning evaluation
77.3%
Better than 78% of models compared
Last updated Oct 1, 2026
Artificial AnalysisProviders
Choose explicit providers for this model. Auto routing remains available as the default option.
Loading provider options…
Related text models
Compare Qwen3.6 27B Thinking with similar models from the same provider or model family.
Qwen3.6 27B
qwen/qwen3.6-27bQwen3.6 27B is a native vision-language dense model with stronger agentic coding and STEM reasoning than Qwen 3.5 27B. It also improves spatial intelligence (including object localization/detection), plus video understanding, document OCR, and visual-agent workflows.
Qwen3.8 Omni Flash
qwen/qwen3.8-omni-flashQwen3.8 Omni Flash is a fast omni-modal reasoning model for understanding text, images, audio, and video. It is especially suited to meeting summaries, transcripts and subtitles, speaker-aware audiovisual analysis, and long-form content review. It returns text and supports a nearly one-million-token context window, tool calling, and structured output.
Qwen3.8 Max 0902
qwen/qwen3.8-max-0902Qwen3.8 Max 0902 is Alibaba's September 2 checkpoint of its flagship Qwen3.8 Max model for coding, knowledge work, data analysis, and long-running agent workflows. It supports text, image, video, PDF input, selectable thinking, tool calling, structured output, and a near-million-token context window.
Qwen3.8 Flash
qwen/qwen3.8-flashQwen3.8 Flash is Alibaba's latest fast multimodal model, with a million-token context window for coding, agentic workflows, visual understanding, long documents, codebases, and videos.
Qwen3.6 Flash
qwen/qwen3.6-flashQwen3.6 Flash is Alibaba's fast native vision-language model in the Qwen 3.6 family. It improves over 3.5 Flash with stronger coding/agent performance and better spatial intelligence, including object localization and detection.
Qwen 3.8 27B Hemingway
qwen/qwen3.8-27b-hemmingwayQwen 3.8 27B Hemingway is an open-weight NVFP4 multimodal creative finetune for long-form prose, character dialogue, storytelling, and roleplay.