Browse all Qwen text models
Provider logo

Qwen3.8 27B Thinking

qwen/qwen3.8-27b:thinking
Provider logo

Qwen3.8 27B Thinking

qwen/qwen3.8-27b:thinking

Qwen3.8 27B is an open-weight multimodal model from Alibaba for reasoning, coding, visual understanding, tool use, and structured output. This variant enables thinking by default. Requests containing video cost $0.32 per million input tokens and $2.50 per million output tokens.

Added Aug 16, 2026

Model weights

Context Window

262.1K

Max Output

32.8K

Avg output tokens (7d)

2.0K tokens

90%

Input Price (Auto)

$0.15/1M

Output Price (Auto)

$0.70/1M

Cache Read (Auto)

$0.040/1M

Capabilities

Benchmarks

Performance metrics and benchmarks

Sourced from Artificial Analysis.

Intelligence Index

33.9

Better than 89% of models compared

Coding Index

68.1

Better than 79% of models compared

Agentic Index

46.5

Better than 89% of models compared

Agentic work

AutomationBench-AA

Workflow automation with guardrail penalties

48.2%

Better than 70% of models compared

AutomationBench-AA Tasks Completed

Fully completed workflows without guardrail violations

15.7%

Better than 27% of models compared

AA-Briefcase

Agentic knowledge work (Elo)

1398 Elo

Better than 82% of models compared

GDPval-AA v2

Economically valuable tasks (Elo)

1463 Elo

Better than 83% of models compared

Document reasoning

GDP.pdf

Professional PDF reasoning: all-pass rate

16.4%

Better than 66% of models compared

AA-LCR v1.1

Long context reasoning with updated grading

82.0%

Better than 95% of models compared

Reasoning

HLE

Humanity's Last Exam

33.9%

Better than 85% of models compared

CritPt

Research-level physics reasoning

5.4%

Coding

Terminal-Bench v4.0

Practical coding and terminal tasks

5.6%

Better than 62% of models compared

SciCode

Python programming for scientific computing

46.6%

Better than 47% of models compared

Knowledge

AA-Omniscience Accuracy

Proportion of correctly answered questions

15.6%

AA-Omniscience Hallucination Rate

Rate of incorrect answers among non-correct responses

30.3%

Legacy benchmarks

GPQA Diamond (legacy)

Graduate-level scientific reasoning

90.5%

Better than 90% of models compared

AA-LCR (unversioned / legacy)

Long context reasoning evaluation

82.0%

Better than 95% of models compared

GDPval-AA (unversioned / legacy)

Economically valuable tasks

48.2%

Last updated Sep 11, 2026

Artificial Analysis

Providers

Choose explicit providers for this model. Auto routing remains available as the default option.

Loading provider options…

Compare Qwen3.8 27B Thinking with similar models from the same provider or model family.