Claude Sonnet 4vsGLM-5.1

Claude Sonnet 4
GLM-5.1
Specifications
Parameters
744B
Context window
200k
Benchmarks
Nonsense detection
BullshitBench v2
30%Best
22%
Coding
SWE-Bench Verified
72.7%
Next.js coding
Next.js Evals
75%
Agentic terminal coding
Terminal-Bench 2.0
63.5%
Web browsing
BrowseComp
68%
Multidisciplinary reasoning
Humanity's Last Exam · with tools
52.3%
Science
GPQA Diamond
75.4%
86.2%Best
Community preference
Arena Elo (Text)
1468
Community preference (code)
Arena Elo (Code)
1518
Overview
CompanyAnthropicZ.ai
Release dateMay 22 2025Apr 7 2026
AccessProprietaryOpen Weight

Which is better: Claude Sonnet 4 or GLM-5.1?

Claude Sonnet 4 and GLM-5.1 are evenly matched across the 2 benchmarks they both report (BullshitBench v2, GPQA Diamond). Claude Sonnet 4 shipped 320 days before GLM-5.1, so benchmark comparisons should account for the intervening progress.

Claude Sonnet 4 is proprietary, while GLM-5.1 is open weight.

On BullshitBench v2, Claude Sonnet 4 leads at 30% vs GLM-5.1 at 22%. On GPQA Diamond, GLM-5.1 leads at 86.2% vs Claude Sonnet 4 at 75.4%.

Frequently asked questions

Claude Sonnet 4 was released by Anthropic on May 22 2025.

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

GLM-5.1 leads on GPQA Diamond — Claude Sonnet 4 75.4% vs GLM-5.1 86.2%.

Claude Sonnet 4 is a proprietary model released by Anthropic. GLM-5.1 is an open weight model released by Z.ai.

Other comparisons