Compare AI models

Specifications
Parameters
—744B
Context window
500k200k
API pricing
Input price
$2.00$1.00
Output price
$6.00$3.20
Cached input price
$0.30$0.20
Cheapest input
$2.00xAI$0.60StreamLake
Cheapest output
$6.00xAI$1.92StreamLake
$700SpaceXSI list price$216StreamLake · fp8
Benchmarks
BullshitBench v2
55%28%
SWE-Bench Pro
64.7%55.1%
SWE-Bench Multilingual
78%73.3%
Overview
CompanySpaceXSIZ.ai
Release dateJul 8 2026Feb 11 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Grok 4.5 leads GLM-5 on 3 of the 3 benchmarks they both report (BullshitBench v2, SWE-Bench Pro, SWE-Bench Multilingual). GLM-5 is cheaper on both input and output: $1.00 vs $2.00 per million input tokens, and $3.20 vs $6.00 per million output tokens. Figures are base-tier rates. GLM-5 shipped 147 days before Grok 4.5, so benchmark comparisons should account for the intervening progress.

Context windows are 500k (Grok 4.5) vs 200k (GLM-5). Grok 4.5 is closed, while GLM-5 is open weight.

On BullshitBench v2, Grok 4.5 leads at 55% vs GLM-5 at 28%. On SWE-Bench Pro, Grok 4.5 leads at 64.7% vs GLM-5 at 55.1%. On SWE-Bench Multilingual, Grok 4.5 leads at 78% vs GLM-5 at 73.3%.