Private AI
Qwen3.8 Max is Qwen's 2.4T-parameter flagship model for coding, knowledge work, full-stack development, data analysis, and long-running agent workflows in non-thinking mode. 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
65.5K
Input Price (Auto)
$2.00/1M
Output Price (Auto)
$6.00/1M
Cache Read (Auto)
$0.25/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
58.1
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Coding Index
71.8
Agentic Index
58.4
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 90% of models compared
GDPval-AA
Economically valuable tasks
62.0%
CritPt
Research-level physics reasoning
20.0%
SciCode
Python programming for scientific computing
52.9%
Better than 95% of models compared
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 8, 2026
Artificial Analysis