Claude Opus 4.6vsGLM-5
Claude Opus 4.6 | GLM-5 | |
|---|---|---|
| Specifications | ||
Parameters | — | 744B |
| Benchmarks | ||
Nonsense detection BullshitBench v2Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | 87%Best | 28% |
Coding SWE-Bench VerifiedReal coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 80.8%Best | 77.8% |
Multilingual coding SWE-Bench MultilingualLike SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | — | 73.3% |
Next.js coding Next.js EvalsVercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. | 75% | — |
Agentic terminal coding Terminal-Bench 2.0Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. | — | 56.2% |
Web browsing BrowseCompCan the AI browse the web and track down hard-to-find answers? Higher is better. | 83.7%Best | 75.9% |
Multidisciplinary reasoning Humanity's Last Exam · with toolsHumanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | 53%Best | 50.4% |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 91.3%Best | 86% |
Community preference Arena Elo (Text)Real people chat with two anonymous AIs side by side and vote for the answer they prefer. Votes become a chess-style Elo rating on arena.ai — it measures which AI people actually like, not test scores. Higher is better. | 1504 | — |
Community preference (code) Arena Elo (Code)Like the text arena, but people vote on which AI writes better code. The votes become a chess-style Elo rating on arena.ai. Higher is better. | 1543Best | 1435 |
| Overview | ||
| Company | Anthropic | Z.ai |
| Release date | Feb 5 2026 | Feb 12 2026 |
| Access | Proprietary | Open 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.