Grok 4.5vsGLM-5.3-Flash
Grok 4.5 | GLM-5.3-Flash | |
|---|---|---|
| Specifications | ||
ParametersA rough measure of how big the model is. More parameters usually means more capable and more expensive to run, though it is a poor guide on its own — a smaller, newer model often beats a larger, older one. | — | 320B |
Context windowHow much text the model can hold in mind at once — your question, any documents you attach, the conversation so far, and its own reply. Go past it and the earliest part falls out of view. | — | 1M |
| API pricingUSD per 1M tokens · lower wins · base tier | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | $2.00 | — |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | $6.00 | — |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | $0.30 | — |
| Benchmarks | ||
DeepSWE 1.1Agentic coding — Artificial 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% | 63.4% |
Terminal-Bench 2.1Agentic terminal coding — Can 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% | 84.3% |
GDPval-AA v2Knowledge work — economically valuable knowledge work (v2, re-based Elo) | 1526 | 1773 |
| BenchmarksPublished by one model only | ||
BullshitBench v2Nonsense detection — Given 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% | — |
Gray Swan IPI · k = 1Prompt injection robustness — Attackers 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% | — |
Gray Swan IPI · k = 10Prompt injection robustness — Attackers 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% | — |
Gray Swan IPI · k = 15Prompt injection robustness — Attackers 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% | — |
SWE-Bench ProAgentic coding — Can 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% | — |
SWE-Bench MultilingualMultilingual coding — Like SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | 78% | — |
DeepSWE 1.0Agentic coding — Artificial 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% | — |
FrontierCode v1.1 (Extended) · extended splitAgentic coding — frontier-difficulty agentic coding tasks (v1.1, extended split) | 56.6% | — |
APEX-SWEExpert software engineering — expert-level software-engineering tasks (AI Productivity Index) | 53.6% | — |
Next.js EvalsNext.js coding — Vercel'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% | — |
Frontier-Bench v0.1Agentic computer work — A 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% | — |
Terminal-Bench 3.0Agentic terminal coding — command-line task completion (v3.0, much harder task set) | 15.7% | — |
APEX-AgentsExpert agentic work — expert-level agentic work tasks (AI Productivity Index) | 47.1% | — |
Humanity's Last Exam · with toolsMultidisciplinary reasoning — Humanity'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. | — | 55.3% |
Agent's Last Exam · pass@1Agentic computer use — A hard set of desktop and operating-system tasks an AI agent has to finish by looking at the screen and working the machine itself. The score is the share it passes outright — partial credit does not count. Higher is better. | — | 26.3% |
AutomationBenchBusiness workflows — Tests whether the AI can run real multi-step business workflows — the kind of end-to-end office processes companies want to automate — from start to finish. Higher is better. | — | 48.8% |
Harvey's Legal Agent BenchmarkAgentic legal work — Harvey'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% | — |
MedScribeMedical admin work — Can the AI support doctors with their administrative work, like notes and paperwork? Created by Vals AI. Higher is better. | 86.88% | — |
AA Intelligence IndexOverall intelligence — Artificial Analysis composite intelligence index across evals | 56 | — |
AA-BriefcaseKnowledge work — Artificial Analysis agentic office-work eval (Elo) | 1313 | — |
| Overview | ||
| Company | SpaceXAI | Z.ai |
| Release date | Jul 8 2026 | Aug 26 2026 |
| Access | Proprietary | Open Weight |
Other comparisons
Grok 4.5vsClaude Opus 5GLM-5.3-FlashvsClaude Opus 5Grok 4.5vsGPT-5.6 SolGLM-5.3-FlashvsGPT-5.6 SolGrok 4.5vsGemini 3.7 FlashGLM-5.3-FlashvsGemini 3.7 FlashGrok 4.5vsMuse GlimmerGLM-5.3-FlashvsMuse GlimmerGrok 4.5vsDeepSeek-V4-Pro-0813GLM-5.3-FlashvsDeepSeek-V4-Pro-0813Grok 4.5vsMistral Medium 3.5GLM-5.3-FlashvsMistral Medium 3.5
Frequently asked questions
GLM-5.3-Flash leads Grok 4.5 on 3 of the 3 benchmarks they both report (DeepSWE 1.1, Terminal-Bench 2.1, GDPval-AA v2). Only Grok 4.5 has a verified first-party API price: $2.00 per million input tokens and $6.00 per million output tokens. No pay-as-you-go API rate is tracked for GLM-5.3-Flash. Grok 4.5 shipped 49 days before GLM-5.3-Flash, so benchmark comparisons should account for the intervening progress.
Grok 4.5 is proprietary, while GLM-5.3-Flash is open weight.
On DeepSWE 1.1, GLM-5.3-Flash leads at 63.4% vs Grok 4.5 at 54%. On Terminal-Bench 2.1, GLM-5.3-Flash leads at 84.3% vs Grok 4.5 at 83.3%. On GDPval-AA v2, GLM-5.3-Flash leads at 1773 vs Grok 4.5 at 1526.
Grok 4.5 was released by SpaceXAI on Jul 8 2026.
GLM-5.3-Flash was released by Z.ai on Aug 26 2026.
GLM-5.3-Flash leads on DeepSWE 1.1 — Grok 4.5 54% vs GLM-5.3-Flash 63.4%.
Only Grok 4.5 has a verified first-party API price: $2.00 per million input tokens and $6.00 per million output tokens. No pay-as-you-go API rate is tracked for GLM-5.3-Flash. Rates are pay-as-you-go API prices verified on August 18, 2026.
Grok 4.5 is a proprietary model released by SpaceXAI. GLM-5.3-Flash is an open weight model released by Z.ai.