Provider logo

Qwen3.8 Max Thinking

qwen3.8-max:thinking
Provider logo

Qwen3.8 Max Thinking

qwen3.8-max:thinking

Qwen3.8 Max Thinking enables generation-time reasoning for deeper coding, knowledge work, data analysis, and long-running agent workflows. It supports text, image, video, PDF input, tool calling, structured output, and a near-million-token context window.

Added Aug 3, 2026

Context Window

991.0K

Max Output

131.1K

Input Price (Auto)

$2.00/1M

Output Price (Auto)

$6.00/1M

Cache Read (Auto)

$0.20/1M

Capabilities

Benchmarks

Performance metrics and benchmarks

Sourced from Artificial Analysis.

Intelligence Index

58.1

Better than 98% of models compared

Coding Index

71.8

Better than 91% of models compared

Agentic Index

58.4

Better than 97% of models compared

Reasoning

GPQA Diamond

Graduate-level scientific reasoning

92.7%

Better than 97% of models compared

HLE

Humanity's Last Exam

43.0%

Better than 97% of models compared

AA-LCR

Long context reasoning evaluation

74.3%

Better than 89% of models compared

GDPval-AA

Economically valuable tasks

61.8%

CritPt

Research-level physics reasoning

20.0%

Coding

SciCode

Python programming for scientific computing

52.9%

Better than 94% of models compared

Knowledge

AA-Omniscience Accuracy

Proportion of correctly answered questions

31.9%

AA-Omniscience Hallucination Rate

Rate of incorrect answers among non-correct responses

41.7%

Last updated Aug 16, 2026

Artificial Analysis

Providers

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

Loading provider options…

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