Compare AI models

Specifications
Parameters
1.6T—
Context window
1M1M
API pricing
Cheapest input
$0.8771StreamLake—
Cheapest output
$1.50Relace—
$255Relace · fp4—
Benchmarks
LiveCodeBench
93.5%37.8%
Overview
CompanyDeepSeekQwen
Release dateApr 24 2026Nov 15 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek-V4-Pro leads Qwen2.5-Turbo (1M) on 1 of the 1 benchmark they both report (LiveCodeBench). Qwen2.5-Turbo (1M) shipped 525 days before DeepSeek-V4-Pro, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (DeepSeek-V4-Pro) vs 1M (Qwen2.5-Turbo (1M)). DeepSeek-V4-Pro is open weight, while Qwen2.5-Turbo (1M) is closed.

On LiveCodeBench, DeepSeek-V4-Pro leads at 93.5% vs Qwen2.5-Turbo (1M) at 37.8%.