Grok 4.6vsGLM-4.5
Grok 4.6 | GLM-4.5 | |
|---|---|---|
| Specifications | ||
Parameters | — | 355B |
Context window | — | 128k |
| 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. | — | 8% |
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. | — | 64.2% |
Agentic coding CursorBench v3.2Cursor's own test of harder, real-world coding tasks inside a code editor, on the refreshed v3.2 task set. Scores aren't comparable with v3.1. Higher is better. | 69.9% | — |
Agentic coding DeepSWE 1.1Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better. | 65.9% | — |
Agentic coding FrontierCode v1.1 (Extended) · extended splitfrontier-difficulty agentic coding tasks (v1.1, extended split) | 61.3% | — |
Expert software engineering APEX-SWEexpert-level software-engineering tasks (AI Productivity Index) | 56.4% | — |
Agentic terminal coding Terminal-Bench 3.0command-line task completion (v3.0, much harder task set) | 26% | — |
Expert agentic work APEX-Agentsexpert-level agentic work tasks (AI Productivity Index) | 57.5% | — |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 79.1% |
Agentic legal work Harvey's Legal Agent BenchmarkHarvey's test of whether an AI agent can complete real legal work — drafting and reviewing documents, working with spreadsheets and presentations, and navigating files the way a lawyer's assistant would. Higher is better. | 15.8% | — |
Overall intelligence AA Intelligence IndexArtificial Analysis composite intelligence index across evals | 61 | — |
Knowledge work GDPval-AA v2economically valuable knowledge work (v2, re-based Elo) | 1753 | — |
Knowledge work AA-BriefcaseArtificial Analysis agentic office-work eval (Elo) | 1577 | — |
| Overview | ||
| Company | SpaceXAI | Z.ai |
| Release date | Aug 12 2026 | Jul 28 2025 |
| Access | Proprietary | Open Weight |
Which is better: Grok 4.6 or GLM-4.5?
Grok 4.6 and GLM-4.5 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. GLM-4.5 shipped 380 days before Grok 4.6, so benchmark comparisons should account for the intervening progress.
Grok 4.6 is proprietary, while GLM-4.5 is open weight.
Direct benchmark comparisons are unavailable — Grok 4.6 and GLM-4.5 don't publish scores on any of the same benchmarks.
Frequently asked questions
Grok 4.6 was released by SpaceXAI on Aug 12 2026.
GLM-4.5 was released by Z.ai on Jul 28 2025.
Grok 4.6 is a proprietary model released by SpaceXAI. GLM-4.5 is an open weight model released by Z.ai.