Compare AI models

Specifications
Parameters
671B—
Context window
128k262k
Benchmarks
LiveCodeBench
65.9%91.9%
GPQA Diamond
71.5%91.7%
Overview
CompanyDeepSeekQwen
Release dateJan 20 2025Aug 26 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3.8-Flash-Next leads DeepSeek R1 on 2 of the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). DeepSeek R1 shipped 583 days before Qwen3.8-Flash-Next, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek R1) vs 262k (Qwen3.8-Flash-Next).

On LiveCodeBench, Qwen3.8-Flash-Next leads at 91.9% vs DeepSeek R1 at 65.9%. On GPQA Diamond, Qwen3.8-Flash-Next leads at 91.7% vs DeepSeek R1 at 71.5%.