Compare AI models

Specifications
Parameters
671B30B
Context window
128k200k
API pricing
Input price
—$0.00
Output price
—$0.00
Cached input price
—$0.00
Cheapest input
$0.2088GMICloud—
Cheapest output
$0.3096GMICloud—
$57.24GMICloud · fp8$0.00Z.ai list price
Benchmarks
SWE-Bench Verified
73.1%59.2%
LiveCodeBench
83.3%64%
BrowseComp
51.4%42.8%
AIME 2025
93.1%91.6%
Overview
CompanyDeepSeekZ.ai
Release dateDec 1 2025Jan 19 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek-V3.2 leads GLM-4.7-Flash on 4 of the 4 benchmarks they both report (SWE-Bench Verified, LiveCodeBench, BrowseComp, AIME 2025). Only GLM-4.7-Flash has a verified first-party price for an available API: $0.00 per million input tokens and $0.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for DeepSeek-V3.2. DeepSeek-V3.2 shipped 49 days before GLM-4.7-Flash, so benchmark comparisons should account for the intervening progress.

DeepSeek-V3.2 has 671B parameters, while GLM-4.7-Flash has 30B. Context windows are 128k (DeepSeek-V3.2) vs 200k (GLM-4.7-Flash).

On SWE-Bench Verified, DeepSeek-V3.2 leads at 73.1% vs GLM-4.7-Flash at 59.2%. On LiveCodeBench, DeepSeek-V3.2 leads at 83.3% vs GLM-4.7-Flash at 64%. On BrowseComp, DeepSeek-V3.2 leads at 51.4% vs GLM-4.7-Flash at 42.8%. On AIME 2025, DeepSeek-V3.2 leads at 93.1% vs GLM-4.7-Flash at 91.6%.