Compare AI models

Specifications
Parameters
671B—
Context window
128k32k
API pricing
Cheapest input
$0.256DeepInfra—
Cheapest output
$0.712DeepInfra—
$103StreamLake—
Benchmarks
LiveCodeBench
40.5%38.7%
Overview
CompanyDeepSeekQwen
Release dateDec 26 2024Jan 28 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek V3 leads Qwen2.5-Max on 1 of the 1 benchmark they both report (LiveCodeBench). DeepSeek V3 shipped 33 days before Qwen2.5-Max, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek V3) vs 32k (Qwen2.5-Max). DeepSeek V3 is open weight, while Qwen2.5-Max is closed.

On LiveCodeBench, DeepSeek V3 leads at 40.5% vs Qwen2.5-Max at 38.7%.