Claude 3.7 SonnetvsGLM-4.6

Claude 3.7 Sonnet
GLM-4.6
Specifications
Parameters
355B
Context window
200k
Benchmarks
Nonsense detection
BullshitBench v2
49%
Coding
SWE-Bench Verified
62.3%
68%Best
Science
GPQA Diamond
68%
Community preference (code)
Arena Elo (Code)
1339
Overview
CompanyAnthropicZ.ai
Release dateFeb 24 2025Sep 30 2025
AccessProprietaryOpen Weight

Which is better: Claude 3.7 Sonnet or GLM-4.6?

GLM-4.6 leads Claude 3.7 Sonnet on 1 of the 1 benchmark they both report (SWE-Bench Verified). Claude 3.7 Sonnet shipped 218 days before GLM-4.6, so benchmark comparisons should account for the intervening progress.

Claude 3.7 Sonnet is proprietary, while GLM-4.6 is open weight.

On SWE-Bench Verified, GLM-4.6 leads at 68% vs Claude 3.7 Sonnet at 62.3%.

Frequently asked questions

Claude 3.7 Sonnet was released by Anthropic on Feb 24 2025.

GLM-4.6 was released by Z.ai on Sep 30 2025.

GLM-4.6 leads on SWE-Bench Verified — Claude 3.7 Sonnet 62.3% vs GLM-4.6 68%.

Claude 3.7 Sonnet is a proprietary model released by Anthropic. GLM-4.6 is an open weight model released by Z.ai.

Other comparisons