Grok 4.5vsGLM-5.2
Grok 4.5 | GLM-5.2 | |
|---|---|---|
| Specifications | ||
Parameters | — | 744B |
Context window | — | 1M |
| 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. | 54%Best | 31% |
Prompt injection robustness Gray Swan IPI · k = 1Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. Gray Swan's indirect prompt injection benchmark measures how often such an attack succeeds when the attacker gets a single try. Lower is better. | 13.4% | — |
Prompt injection robustness Gray Swan IPI · k = 10Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. This variant gives the attacker 10 tries and counts an attack as successful if any of them works. Lower is better. | 54.2% | — |
Prompt injection robustness Gray Swan IPI · k = 15Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. This variant gives the attacker 15 tries and counts an attack as successful if any of them works. Lower is better. | 60.8% | — |
Agentic coding SWE-Bench ProCan the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better. | 64.7%Best | 62.1% |
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. | 78% | — |
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. | 66.7%Best | 55% |
Agentic coding CursorBench v3.1Cursor's own test of harder, real-world coding tasks inside a code editor. Higher is better. | — | 54.6% |
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. | 54%Best | 44% |
Agentic coding DeepSWE 1.0Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. Higher is better. | 62% | — |
Agentic coding FrontierCode v1.1 (Extended) · extended splitfrontier-difficulty agentic coding tasks (v1.1, extended split) | 56.6% | — |
Expert software engineering APEX-SWEexpert-level software-engineering tasks (AI Productivity Index) | 53.6% | — |
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. | 83% | 88%Best |
Agentic computer work Frontier-Bench v0.1A hard, ever-evolving set of real computer tasks — coding, system administration, data work, and more — that an AI agent has to complete on its own. Run by the Harbor / Laude Institute team as the successor to Terminal-Bench (v0.1 is the first release of the task set). The score is the share of tasks solved. Higher is better. | 17.8%Best | 5.1% |
Agentic terminal coding Terminal-Bench 3.0command-line task completion (v3.0, much harder task set) | 15.7% | — |
Agentic terminal coding Terminal-Bench 2.1Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | 83.3%Best | 81% |
Expert agentic work APEX-Agentsexpert-level agentic work tasks (AI Productivity Index) | 47.1% | — |
Multidisciplinary reasoning Humanity's Last Exam · no toolsHumanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. | — | 40.5% |
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. | — | 54.7% |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 91.2% |
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. | 12.92% | — |
Medical admin work MedScribeCan the AI support doctors with their administrative work, like notes and paperwork? Created by Vals AI. Higher is better. | 86.88% | — |
Overall intelligence AA Intelligence IndexArtificial Analysis composite intelligence index across evals | 56 | — |
Knowledge work GDPval-AA v2economically valuable knowledge work (v2, re-based Elo) | 1526Best | 1514 |
Knowledge work AA-BriefcaseArtificial Analysis agentic office-work eval (Elo) | 1313 | — |
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. | 1468 | — |
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. | 1555 | 1587Best |
| Overview | ||
| Company | SpaceXAI | Z.ai |
| Release date | Jul 8 2026 | Jun 16 2026 |
| Access | Proprietary | Open Weight |
Which is better: Grok 4.5 or GLM-5.2?
Grok 4.5 leads GLM-5.2 on 7 of the 9 benchmarks they both report. GLM-5.2 shipped 22 days before Grok 4.5, so benchmark comparisons should account for the intervening progress.
Grok 4.5 is proprietary, while GLM-5.2 is open weight.
On BullshitBench v2, Grok 4.5 leads at 54% vs GLM-5.2 at 31%. On SWE-Bench Pro, Grok 4.5 leads at 64.7% vs GLM-5.2 at 62.1%. On CursorBench v3.2, Grok 4.5 leads at 66.7% vs GLM-5.2 at 55%. On DeepSWE 1.1, Grok 4.5 leads at 54% vs GLM-5.2 at 44%. On Next.js Evals, GLM-5.2 leads at 88% vs Grok 4.5 at 83%. On Frontier-Bench v0.1, Grok 4.5 leads at 17.8% vs GLM-5.2 at 5.1%. On Terminal-Bench 2.1, Grok 4.5 leads at 83.3% vs GLM-5.2 at 81%. On GDPval-AA v2, Grok 4.5 leads at 1526 vs GLM-5.2 at 1514. On Arena Elo (Code), GLM-5.2 leads at 1587 vs Grok 4.5 at 1555.
Frequently asked questions
Grok 4.5 was released by SpaceXAI on Jul 8 2026.
GLM-5.2 was released by Z.ai on Jun 16 2026.
Grok 4.5 leads on SWE-Bench Pro — Grok 4.5 64.7% vs GLM-5.2 62.1%.
Grok 4.5 is a proprietary model released by SpaceXAI. GLM-5.2 is an open weight model released by Z.ai.