Compare AI models

Specifications
Parameters
671B—
Context window
128k262k
Benchmarks
LiveCodeBench
88.7%91.9%
GPQA Diamond
85.7%91.7%
Overview
CompanyDeepSeekQwen
Release dateDec 1 2025Aug 26 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3.8-Flash-Next leads DeepSeek-V3.2-Speciale on 2 of the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). DeepSeek-V3.2-Speciale shipped 268 days before Qwen3.8-Flash-Next, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek-V3.2-Speciale) vs 262k (Qwen3.8-Flash-Next).

On LiveCodeBench, Qwen3.8-Flash-Next leads at 91.9% vs DeepSeek-V3.2-Speciale at 88.7%. On GPQA Diamond, Qwen3.8-Flash-Next leads at 91.7% vs DeepSeek-V3.2-Speciale at 85.7%.