Compare AI models

Specifications
Parameters
671B—
Context window
128k1M
API pricing
Cheapest input
$0.256DeepInfra—
Cheapest output
$0.712DeepInfra—
$103StreamLake—
Benchmarks
LiveCodeBench
40.5%37.8%
Overview
CompanyDeepSeekQwen
Release dateDec 26 2024Nov 15 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek V3 leads Qwen2.5-Turbo (1M) on 1 of the 1 benchmark they both report (LiveCodeBench). Qwen2.5-Turbo (1M) shipped 41 days before DeepSeek V3, so benchmark comparisons should account for the intervening progress.

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

On LiveCodeBench, DeepSeek V3 leads at 40.5% vs Qwen2.5-Turbo (1M) at 37.8%.