Grok 4.20 BetavsGLM-5.2

Grok 4.20 Beta
GLM-5.2
Specifications
Parameters
744B
Context window
1M
Benchmarks
Nonsense detection
BullshitBench v2
56%Best
31%
Agentic coding
SWE-Bench Pro
62.1%
Agentic coding
CursorBench v3.2
55%
Agentic coding
CursorBench v3.1
54.6%
Agentic coding
DeepSWE 1.1
44%
Next.js coding
Next.js Evals
88%
Agentic computer work
Frontier-Bench v0.1
5.1%
Agentic terminal coding
Terminal-Bench 2.1
81%
Multidisciplinary reasoning
Humanity's Last Exam · no tools
40.5%
Multidisciplinary reasoning
Humanity's Last Exam · with tools
54.7%
Abstract reasoning
ARC-AGI-2
53.3%
Science
GPQA Diamond
91.2%
Knowledge work
GDPval-AA v2
1514
Community preference
Arena Elo (Text)
1475
Community preference (code)
Arena Elo (Code)
1587
Overview
CompanySpaceXAIZ.ai
Release dateFeb 17 2026Jun 16 2026
AccessProprietaryOpen Weight

Which is better: Grok 4.20 Beta or GLM-5.2?

Grok 4.20 Beta leads GLM-5.2 on 1 of the 1 benchmark they both report (BullshitBench v2). Grok 4.20 Beta shipped 119 days before GLM-5.2, so benchmark comparisons should account for the intervening progress.

Grok 4.20 Beta is proprietary, while GLM-5.2 is open weight.

On BullshitBench v2, Grok 4.20 Beta leads at 56% vs GLM-5.2 at 31%.

Frequently asked questions

Grok 4.20 Beta was released by SpaceXAI on Feb 17 2026.

GLM-5.2 was released by Z.ai on Jun 16 2026.

Grok 4.20 Beta is a proprietary model released by SpaceXAI. GLM-5.2 is an open weight model released by Z.ai.

Other comparisons