Compare AI models

Specifications
Parameters
1.6T—
Context window
1M200k
API pricing
Cheapest input
$0.8771StreamLake—
Cheapest output
$1.50Relace—
$255Relace · fp4—
Benchmarks
BullshitBench v2
14%31%
Overview
CompanyDeepSeekZ.ai
Release dateApr 24 2026Mar 15 2026
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

GLM-5-Turbo leads DeepSeek-V4-Pro on 1 of the 1 benchmark they both report (BullshitBench v2). GLM-5-Turbo shipped 40 days before DeepSeek-V4-Pro, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (DeepSeek-V4-Pro) vs 200k (GLM-5-Turbo). DeepSeek-V4-Pro is open weight, while GLM-5-Turbo is closed.

On BullshitBench v2, GLM-5-Turbo leads at 31% vs DeepSeek-V4-Pro at 14%.