Claude 3 SonnetvsGLM-5.2

Claude 3 Sonnet
GLM-5.2
Specifications
Parameters
744B
Context window
1M
Benchmarks
Nonsense detection
BullshitBench v2
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%
Science
GPQA Diamond
40.4%
91.2%Best
Knowledge work
GDPval-AA v2
1514
Community preference (code)
Arena Elo (Code)
1587
Overview
CompanyAnthropicZ.ai
Release dateMar 4 2024Jun 16 2026
AccessProprietaryOpen Weight

Which is better: Claude 3 Sonnet or GLM-5.2?

GLM-5.2 leads Claude 3 Sonnet on 1 of the 1 benchmark they both report (GPQA Diamond). Claude 3 Sonnet shipped 834 days before GLM-5.2, so benchmark comparisons should account for the intervening progress.

Claude 3 Sonnet is proprietary, while GLM-5.2 is open weight.

On GPQA Diamond, GLM-5.2 leads at 91.2% vs Claude 3 Sonnet at 40.4%.

Frequently asked questions

Claude 3 Sonnet was released by Anthropic on Mar 4 2024.

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

GLM-5.2 leads on GPQA Diamond — Claude 3 Sonnet 40.4% vs GLM-5.2 91.2%.

Claude 3 Sonnet is a proprietary model released by Anthropic. GLM-5.2 is an open weight model released by Z.ai.

Other comparisons