Compare AI models

Specifications
Parameters
671B9B/32B
Context window
128k128k
API pricing
Cheapest input
$0.27SiliconFlow—
Cheapest output
$0.41SiliconFlow—
$74.50SiliconFlow · fp8—
Benchmarks
LiveCodeBench
74.1%59.1%
AIME 2025
89.3%63.6%
Overview
CompanyDeepSeekZ.ai
Release dateSep 29 2025Apr 14 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V3.2 Exp leads GLM-Z1-0414 on 2 of the 2 benchmarks they both report (LiveCodeBench, AIME 2025). GLM-Z1-0414 shipped 168 days before DeepSeek V3.2 Exp, so benchmark comparisons should account for the intervening progress.

DeepSeek V3.2 Exp has 671B parameters, while GLM-Z1-0414 has 9B/32B. Context windows are 128k (DeepSeek V3.2 Exp) vs 128k (GLM-Z1-0414).

On LiveCodeBench, DeepSeek V3.2 Exp leads at 74.1% vs GLM-Z1-0414 at 59.1%. On AIME 2025, DeepSeek V3.2 Exp leads at 89.3% vs GLM-Z1-0414 at 63.6%.