Compare AI models

Specifications
Parameters
—30B
Context window
400k200k
API pricing
Input price
$1.75$0.00
Output price
$14.00$0.00
Cached input price
$0.175$0.00
Cheapest input
$0.875OpenAI—
Cheapest output
$7.00OpenAI—
$1,050OpenAI list price$0.00Z.ai list price
Benchmarks
SWE-Bench Verified
80%59.2%
BrowseComp
65.8%42.8%
AIME 2025
100%91.6%
Overview
CompanyOpenAIZ.ai
Release dateDec 11 2025Jan 19 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

GPT-5.2 leads GLM-4.7-Flash on 3 of the 3 benchmarks they both report (SWE-Bench Verified, BrowseComp, AIME 2025). GLM-4.7-Flash is cheaper on both input and output: $0.00 vs $1.75 per million input tokens, and $0.00 vs $14.00 per million output tokens. GPT-5.2 shipped 39 days before GLM-4.7-Flash, so benchmark comparisons should account for the intervening progress.

Context windows are 400k (GPT-5.2) vs 200k (GLM-4.7-Flash). GPT-5.2 is closed, while GLM-4.7-Flash is open weight.

On SWE-Bench Verified, GPT-5.2 leads at 80% vs GLM-4.7-Flash at 59.2%. On BrowseComp, GPT-5.2 leads at 65.8% vs GLM-4.7-Flash at 42.8%. On AIME 2025, GPT-5.2 leads at 100% vs GLM-4.7-Flash at 91.6%.