Grok 4.20 BetavsGLM-4.5

Grok 4.20 Beta
GLM-4.5
Specifications
Parameters
355B
Context window
128k
API pricing
Input price
$1.25$0.60
Output price
$2.50$2.20
Cached input price
$0.20$0.11
Benchmarks
BullshitBench v2
56%8%
SWE-Bench Verified
76.7%64.2%
Benchmarks
ARC-AGI-2
53.3%
GPQA Diamond
79.1%
Overview
CompanySpaceXAIZ.ai
Release dateFeb 17 2026Jul 28 2025
AccessProprietaryOpen Weight

Other comparisons

Grok 4.20 BetavsClaude Fable 5.1GLM-4.5vsClaude Fable 5.1Grok 4.20 BetavsGPT-6 AstraGLM-4.5vsGPT-6 AstraGrok 4.20 BetavsGemini 3.8 FlashGLM-4.5vsGemini 3.8 FlashGrok 4.20 BetavsMuse Spark 1.3GLM-4.5vsMuse Spark 1.3Grok 4.20 BetavsDeepSeek-V4.1-FlashGLM-4.5vsDeepSeek-V4.1-FlashGrok 4.20 BetavsMistral Medium 3.5GLM-4.5vsMistral Medium 3.5

Frequently asked questions

Grok 4.20 Beta leads GLM-4.5 on 2 of the 2 benchmarks they both report (BullshitBench v2, SWE-Bench Verified). GLM-4.5 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-4.5 shipped 204 days before Grok 4.20 Beta, so benchmark comparisons should account for the intervening progress.

Grok 4.20 Beta is proprietary, while GLM-4.5 is open weight.

On BullshitBench v2, Grok 4.20 Beta leads at 56% vs GLM-4.5 at 8%. On SWE-Bench Verified, Grok 4.20 Beta leads at 76.7% vs GLM-4.5 at 64.2%.