Grok 4.20 BetavsGLM-4.7

Grok 4.20 Beta
GLM-4.7
Specifications
Context window
128k
API pricing
Input price
$1.25$0.60
Output price
$2.50$2.20
Cached input price
$0.20$0.11
Cheapest input
$0.40DeepInfra
Cheapest output
$1.75DeepInfra
Benchmarks
SWE-Bench Verified
76.7%73.8%
Benchmarks
BullshitBench v2
56%
LiveCodeBench
84.9%
Terminal-Bench 2.0
41%
BrowseComp
52%
Humanity's Last Exam · no tools
24.8%
Humanity's Last Exam · with tools
42.8%
ARC-AGI-2
53.3%
GPQA Diamond
85.7%
Overview
CompanySpaceXAIZ.ai
Release dateFeb 17 2026Dec 22 2025
AccessProprietaryOpen Weight

Other comparisons

Grok 4.20 BetavsClaude Fable 5.1GLM-4.7vsClaude Fable 5.1Grok 4.20 BetavsGPT-6 AstraGLM-4.7vsGPT-6 AstraGrok 4.20 BetavsGemini 3.8 FlashGLM-4.7vsGemini 3.8 FlashGrok 4.20 BetavsMuse Spark 1.3GLM-4.7vsMuse Spark 1.3Grok 4.20 BetavsDeepSeek-V4.1-FlashGLM-4.7vsDeepSeek-V4.1-FlashGrok 4.20 BetavsMistral Medium 3.5GLM-4.7vsMistral Medium 3.5

Frequently asked questions

Grok 4.20 Beta leads GLM-4.7 on 1 of the 1 benchmark they both report (SWE-Bench Verified). GLM-4.7 is cheaper on both input and output: $0.60 vs $1.25 per million input tokens, and $2.20 vs $2.50 per million output tokens. Figures are base-tier rates. GLM-4.7 shipped 57 days before Grok 4.20 Beta, so benchmark comparisons should account for the intervening progress.

Grok 4.20 Beta is proprietary, while GLM-4.7 is open weight.

On SWE-Bench Verified, Grok 4.20 Beta leads at 76.7% vs GLM-4.7 at 73.8%.