Claude Opus 4.6vsGLM-5

Claude Opus 4.6
GLM-5
Specifications
Parameters
744B
Benchmarks
Nonsense detection
BullshitBench v2
87%Best
28%
Coding
SWE-Bench Verified
80.8%Best
77.8%
Multilingual coding
SWE-Bench Multilingual
73.3%
Next.js coding
Next.js Evals
75%
Agentic terminal coding
Terminal-Bench 2.0
56.2%
Web browsing
BrowseComp
83.7%Best
75.9%
Multidisciplinary reasoning
Humanity's Last Exam · with tools
53%Best
50.4%
Science
GPQA Diamond
91.3%Best
86%
Community preference
Arena Elo (Text)
1504
Community preference (code)
Arena Elo (Code)
1543Best
1435
Overview
CompanyAnthropicZ.ai
Release dateFeb 5 2026Feb 12 2026
AccessProprietaryOpen Weight

Which is better: Claude Opus 4.6 or GLM-5?

Claude Opus 4.6 leads GLM-5 on 6 of the 6 benchmarks they both report. Claude Opus 4.6 shipped 7 days before GLM-5, so benchmark comparisons should account for the intervening progress.

Claude Opus 4.6 is proprietary, while GLM-5 is open weight.

On BullshitBench v2, Claude Opus 4.6 leads at 87% vs GLM-5 at 28%. On SWE-Bench Verified, Claude Opus 4.6 leads at 80.8% vs GLM-5 at 77.8%. On BrowseComp, Claude Opus 4.6 leads at 83.7% vs GLM-5 at 75.9%. On Humanity's Last Exam · with tools, Claude Opus 4.6 leads at 53% vs GLM-5 at 50.4%. On GPQA Diamond, Claude Opus 4.6 leads at 91.3% vs GLM-5 at 86%. On Arena Elo (Code), Claude Opus 4.6 leads at 1543 vs GLM-5 at 1435.

Frequently asked questions

Claude Opus 4.6 was released by Anthropic on Feb 5 2026.

GLM-5 was released by Z.ai on Feb 12 2026.

Claude Opus 4.6 leads on SWE-Bench Verified — Claude Opus 4.6 80.8% vs GLM-5 77.8%.

Claude Opus 4.6 leads on Humanity's Last Exam · with tools — Claude Opus 4.6 53% vs GLM-5 50.4%.

Claude Opus 4.6 is a proprietary model released by Anthropic. GLM-5 is an open weight model released by Z.ai.

Other comparisons