Compare AI models

Specifications
Parameters
671B>1T
Context window
128k256k
Benchmarks
LiveCodeBench
88.7%85.9%
Humanity's Last Exam · text only, no tools
30.6%30.2%
GPQA Diamond
85.7%87.4%
Overview
CompanyDeepSeekQwen
Release dateDec 1 2025Jan 26 2026
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek-V3.2-Speciale leads Qwen3-Max-Thinking on 2 of the 3 benchmarks they both report (LiveCodeBench, Humanity's Last Exam, GPQA Diamond). DeepSeek-V3.2-Speciale shipped 56 days before Qwen3-Max-Thinking, so benchmark comparisons should account for the intervening progress.

DeepSeek-V3.2-Speciale has 671B parameters, while Qwen3-Max-Thinking has >1T. Context windows are 128k (DeepSeek-V3.2-Speciale) vs 256k (Qwen3-Max-Thinking). DeepSeek-V3.2-Speciale is open weight, while Qwen3-Max-Thinking is closed.

On LiveCodeBench, DeepSeek-V3.2-Speciale leads at 88.7% vs Qwen3-Max-Thinking at 85.9%. On Humanity's Last Exam · text only, no tools, DeepSeek-V3.2-Speciale leads at 30.6% vs Qwen3-Max-Thinking at 30.2%. On GPQA Diamond, Qwen3-Max-Thinking leads at 87.4% vs DeepSeek-V3.2-Speciale at 85.7%.