Compare AI models

Specifications
Parameters
1.6T27B
Context window
1M256k
API pricing
Cheapest input
$0.8771StreamLake—
Cheapest output
$1.50Relace—
$255Relace · fp4—
Benchmarks
LiveCodeBench
93.5%83.9%
GPQA Diamond
90.1%87.8%
Overview
CompanyDeepSeekQwen
Release dateApr 24 2026Apr 22 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek-V4-Pro leads Qwen3.6-27B on 2 of the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). Qwen3.6-27B shipped 2 days before DeepSeek-V4-Pro, so benchmark comparisons should account for the intervening progress.

DeepSeek-V4-Pro has 1.6T parameters, while Qwen3.6-27B has 27B. Context windows are 1M (DeepSeek-V4-Pro) vs 256k (Qwen3.6-27B).

On LiveCodeBench, DeepSeek-V4-Pro leads at 93.5% vs Qwen3.6-27B at 83.9%. On GPQA Diamond, DeepSeek-V4-Pro leads at 90.1% vs Qwen3.6-27B at 87.8%.