Compare AI models

Specifications
Parameters
671B—
Context window
128k1M
API pricing
Cheapest input
$0.25DeepInfra—
Cheapest output
$0.95DeepInfra—
$97.50DeepInfra · fp4—
Benchmarks
LiveCodeBench
74.8%37.8%
MMLU-Pro
84.8%64.5%
Overview
CompanyDeepSeekQwen
Release dateAug 21 2025Nov 15 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek V3.1 leads Qwen2.5-Turbo (1M) on 2 of the 2 benchmarks they both report (LiveCodeBench, MMLU-Pro). Qwen2.5-Turbo (1M) shipped 279 days before DeepSeek V3.1, so benchmark comparisons should account for the intervening progress.

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

On LiveCodeBench, DeepSeek V3.1 leads at 74.8% vs Qwen2.5-Turbo (1M) at 37.8%. On MMLU-Pro, DeepSeek V3.1 leads at 84.8% vs Qwen2.5-Turbo (1M) at 64.5%.