Compare AI models

Specifications
Parameters
671B—
Context window
128k1M
API pricing
Cheapest input
$0.259SiliconFlow—
Cheapest output
$0.38DeepInfra—
$71.00DeepInfra · fp4—
Benchmarks
LiveCodeBench
83.3%37.8%
MMLU-Pro
85%64.5%
Overview
CompanyDeepSeekQwen
Release dateDec 1 2025Nov 15 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek-V3.2 leads Qwen2.5-Turbo (1M) on 2 of the 2 benchmarks they both report (LiveCodeBench, MMLU-Pro). Qwen2.5-Turbo (1M) shipped 381 days before DeepSeek-V3.2, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek-V3.2) vs 1M (Qwen2.5-Turbo (1M)). DeepSeek-V3.2 is open weight, while Qwen2.5-Turbo (1M) is closed.

On LiveCodeBench, DeepSeek-V3.2 leads at 83.3% vs Qwen2.5-Turbo (1M) at 37.8%. On MMLU-Pro, DeepSeek-V3.2 leads at 85% vs Qwen2.5-Turbo (1M) at 64.5%.