Grok 4.20 BetavsGLM-5.1

Grok 4.20 Beta
GLM-5.1
Specifications
Parameters
744B
Context window
200k
API pricing
Input price
$1.25$1.40
Output price
$2.50$4.40
Cached input price
$0.20$0.26
Benchmarks
BullshitBench v2
56%22%
Arena Elo (Text)
14751468
Benchmarks
Next.js Evals
75%
Terminal-Bench 2.0
63.5%
BrowseComp
68%
Humanity's Last Exam · with tools
52.3%
ARC-AGI-2
53.3%
GPQA Diamond
86.2%
Arena Elo (Code)
1510
Overview
CompanySpaceXAIZ.ai
Release dateFeb 17 2026Apr 7 2026
AccessProprietaryOpen Weight

Frequently asked questions

Grok 4.20 Beta leads GLM-5.1 on 2 of the 2 benchmarks they both report (BullshitBench v2, Arena Elo (Text)). Grok 4.20 Beta is cheaper on both input and output: $1.25 vs $1.40 per million input tokens, and $2.50 vs $4.40 per million output tokens. Figures are base-tier rates. Grok 4.20 Beta shipped 49 days before GLM-5.1, so benchmark comparisons should account for the intervening progress.

Grok 4.20 Beta is proprietary, while GLM-5.1 is open weight.

On BullshitBench v2, Grok 4.20 Beta leads at 56% vs GLM-5.1 at 22%. On Arena Elo (Text), Grok 4.20 Beta leads at 1475 vs GLM-5.1 at 1468.

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

GLM-5.1 was released by Z.ai on Apr 7 2026.

Grok 4.20 Beta is cheaper on both input and output: $1.25 vs $1.40 per million input tokens, and $2.50 vs $4.40 per million output tokens. Figures are base-tier rates. Rates are pay-as-you-go API prices verified on August 18, 2026.

Grok 4.20 Beta is a proprietary model released by SpaceXAI. GLM-5.1 is an open weight model released by Z.ai.

Other comparisons