Experimental release of Qwen's reasoning model. Great at coding and math, but still in development so may exhibit odd bugs. Not production-ready.
Added Feb 27, 2025
Context Window
32.8K
Max Output
32.8K
Input Price (Auto)
$0.20/1M
Output Price (Auto)
$0.20/1M
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
9.5
Document reasoning
AA-LCR v1.1
Long context reasoning with updated grading
26.7%
Better than 28% of models compared
Reasoning
HLE
Humanity's Last Exam
7.3%
Better than 44% of models compared
IFBench
Instruction-following benchmark
38.8%
Better than 35% of models compared
Coding
LiveCodeBench
Contamination-free coding benchmark
63.1%
Better than 69% of models compared
Math
AIME 2025
American Invitational Mathematics Examination 2025
29.0%
Better than 30% of models compared
AIME
American Invitational Mathematics Examination
78.0%
Better than 87% of models compared
Math-500
Diverse mathematical problem solving benchmark
95.7%
Better than 81% of models compared
Knowledge
MMLU-Pro
Professional and academic subject knowledge
76.4%
Better than 54% of models compared
Legacy benchmarks
GPQA Diamond (legacy)
Graduate-level scientific reasoning
59.3%
Better than 34% of models compared
AA-LCR (unversioned / legacy)
Long context reasoning evaluation
26.7%
Better than 28% of models compared
Last updated Sep 29, 2026
Artificial AnalysisRelated text models
Compare Qwen QwQ 32B Preview with similar models from the same provider or model family.
Qwen 2.5 Coder 32b
qwen/qwen2.5-coder-32b-instructThe latest series of Code-Specific Qwen large language models.
Qwen 3 32b
qwen/qwen3-32bQwen 3 32b is a 32b model. Supports switching between thinking and non thinking: trigger thinking with /think and /no_think anywhere in a prompt or system message to toggle chain-of-thought reasoning.
Qwen3.8 Max Prime
qwen/qwen3.8-max-primeQwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max for coding, complex analysis, and long-running agent workflows. It accepts text, image, and video input, supports tool calling and structured output, and has a 1M-token context window. Reasoning is always enabled.
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.
Qwen 3.8 27B Cybersecurity
qwen/qwen3.8-27b-cybersecurityQwen 3.8 27B Cybersecurity is a cybersecurity-focused variant based on the uncensored model, with provider moderation for illegal activities. It supports optional reasoning, image understanding, tool calling, and a 262,144-token context window.
Qwen 3.8 27B Queen
qwen/qwen3.8-27b-queenQwen 3.8 27B Queen is an FP8 open-weight roleplay finetune with image understanding, tool calling, optional reasoning, and a 524,288-token context window.