Qwen3 Max. The latest Qwen 3 model (5 september 2025). Higher accuracy in coding and science, better instruction following, and optimized for tool calling.
Added Sep 5, 2025
Context Window
256.0K
Max Output
32.8K
Input Price (Auto)
$1.20/1M
Output Price (Auto)
$6.00/1M
Cache Read (Auto)
$0.60/1M
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
19.4
Reasoning
GPQA Diamond
Graduate-level scientific reasoning
76.4%
Better than 62% of models compared
HLE
Humanity's Last Exam
10.1%
Better than 57% of models compared
IFBench
Instruction-following benchmark
48.0%
Better than 57% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
32.7%
Better than 41% of models compared
AA-LCR
Long context reasoning evaluation
42.3%
Better than 48% of models compared
Coding
SciCode
Python programming for scientific computing
37.0%
Better than 60% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
19.7%
Better than 59% of models compared
LiveCodeBench
Contamination-free coding benchmark
65.1%
Better than 72% of models compared
Math
AIME 2025
American Invitational Mathematics Examination 2025
75.0%
Better than 70% of models compared
Knowledge
MMLU-Pro
Professional and academic subject knowledge
83.8%
Better than 87% of models compared
Last updated Aug 18, 2026
Artificial AnalysisProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Related text models
Compare Qwen3 Max with similar models from the same provider or model family.
Qwen3.8 2.4T A95B (Max)
qwen/qwen3.8-2.4t-a95bThis is the same underlying model as Qwen3.8 Max, exposed under its architecture-based 2.4T A95B name for easier discovery. It uses the identical routing, pricing, capabilities, and non-thinking mode.
Qwen 3.8 27B Fable
qwen/qwen3.8-27b-fableQwen 3.8 27B Fable is an open-weight multimodal creative finetune for expressive dialogue, long-form storytelling, character work, and roleplay.
Qwen 3.8 27B Uncensored Thinking
qwen/qwen3.8-27b-uncensored:thinkingQwen 3.8 27B Uncensored with thinking enabled for more deliberate creative work, coding, multimodal analysis, tool use, and long-context problem solving.
Qwen 3.6 35B A3B Uncensored Thinking
qwen/qwen3.6-35b-a3b-uncensored:thinkingQwen 3.6 35B A3B Uncensored with thinking enabled for more deliberate coding, multimodal analysis, tool use, and complex chat tasks.
Qwen 3.8 27B Obliterated
qwen/qwen3.8-27b-obliteratedQwen 3.8 27B Obliterated is an open-weight multimodal model LoRA-tuned for fewer refusals across chat, coding, reasoning, tool use, and long-context work.
Qwen 3.8 27B Obliterated Thinking
qwen/qwen3.8-27b-obliterated:thinkingQwen 3.8 27B Obliterated with thinking enabled for more deliberate creative work, coding, multimodal analysis, tool use, and long-context problem solving.