Compare AI models

Specifications
Parameters
284B—
Context window
1M200k
API pricing
Cheapest input
$0.05Baidu—
Cheapest output
$0.10Baidu—
$15.00Baidu · fp8—
Benchmarks
BullshitBench v2
18%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-Flash on 1 of the 1 benchmark they both report (BullshitBench v2). GLM-5-Turbo shipped 40 days before DeepSeek-V4-Flash, so benchmark comparisons should account for the intervening progress.

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

On BullshitBench v2, GLM-5-Turbo leads at 31% vs DeepSeek-V4-Flash at 18%.