Claude Opus 4.8vsGLM-5.3-Flash
Claude Opus 4.8 | 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 | 1M |
| API pricingUSD per 1M tokens · lower wins | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | $5.00 | — |
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. | $25.00 | — |
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. | $0.50 | — |
Cheapest inputLowest input rate across third-party providers, excluding the lab itself. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $5.00Amazon Bedrock | — |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $25.00Amazon Bedrock | — |
| Benchmarks | ||
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. | 74.6% | 84.3% |
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. | 57.9% | 55.3% |
GDPval-AA v2Knowledge work — economically valuable knowledge work (v2, re-based Elo) | 1600 | 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. | 95% | — |
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. | 0.5% | — |
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. | 4.1% | — |
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. | 5.5% | — |
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. | 69.2% | — |
SWE-Bench VerifiedCoding — Real 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. | 88.6% | — |
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. | 84.4% | — |
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. | — | 63.4% |
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. | 55.8% | — |
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. | 88% | — |
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. | 21.1% | — |
BU BenchBrowser agent — Can the AI drive a real web browser to finish tasks — clicking, filling forms, and navigating sites the way a person would? Run by Browser Use on their BU Bench task set. Higher is better. | 74% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 84.3% | — |
Humanity's Last Exam · no toolsMultidisciplinary reasoning — Humanity'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. | 49.8% | — |
OSWorld-VerifiedAgentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | 83.4% | — |
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% |
Finance Agent v2Agentic financial analysis — Tests the AI on real financial-analysis work, like digging through reports and making sound decisions. Higher is better. | 53.9% | — |
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. | 9.58% | — |
TaxEval v2Tax questions — A set of real tax questions created by Vals AI — can the AI give accurate answers about tax rules and filings? Higher is better. | 75.63% | — |
MedScribeMedical admin work — Can the AI support doctors with their administrative work, like notes and paperwork? Created by Vals AI. Higher is better. | 85.75% | — |
GDPval-AAKnowledge work — Measures how well the AI does economically valuable knowledge work, judged against human experts. Shown as a rating (like a chess Elo) — higher is better. | 1890 | — |
| Overview | ||
| Company | Anthropic | Z.ai |
| Release date | May 28 2026 | Aug 26 2026 |
| Access | Proprietary | Open Weight |
Other comparisons
Claude Opus 4.8vsGPT-5.6 SolGLM-5.3-FlashvsGPT-5.6 SolClaude Opus 4.8vsGemini 3.7 FlashGLM-5.3-FlashvsGemini 3.7 FlashClaude Opus 4.8vsMuse GlimmerGLM-5.3-FlashvsMuse GlimmerClaude Opus 4.8vsGrok 4.6GLM-5.3-FlashvsGrok 4.6Claude Opus 4.8vsDeepSeek-V4-Pro-0813GLM-5.3-FlashvsDeepSeek-V4-Pro-0813Claude Opus 4.8vsMistral Medium 3.5GLM-5.3-FlashvsMistral Medium 3.5
Frequently asked questions
GLM-5.3-Flash leads Claude Opus 4.8 on 2 of the 3 benchmarks they both report (Terminal-Bench 2.1, Humanity's Last Exam, GDPval-AA v2). Only Claude Opus 4.8 has a verified first-party API price: $5.00 per million input tokens and $25.00 per million output tokens. No pay-as-you-go API rate is tracked for GLM-5.3-Flash. Claude Opus 4.8 shipped 90 days before GLM-5.3-Flash, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Claude Opus 4.8) vs 1M (GLM-5.3-Flash). Claude Opus 4.8 is proprietary, while GLM-5.3-Flash is open weight.
On Terminal-Bench 2.1, GLM-5.3-Flash leads at 84.3% vs Claude Opus 4.8 at 74.6%. On Humanity's Last Exam · with tools, Claude Opus 4.8 leads at 57.9% vs GLM-5.3-Flash at 55.3%. On GDPval-AA v2, GLM-5.3-Flash leads at 1773 vs Claude Opus 4.8 at 1600.
Claude Opus 4.8 was released by Anthropic on May 28 2026.
GLM-5.3-Flash was released by Z.ai on Aug 26 2026.
GLM-5.3-Flash leads on Terminal-Bench 2.1 — Claude Opus 4.8 74.6% vs GLM-5.3-Flash 84.3%.
Claude Opus 4.8 leads on Humanity's Last Exam · with tools — Claude Opus 4.8 57.9% vs GLM-5.3-Flash 55.3%.
Only Claude Opus 4.8 has a verified first-party API price: $5.00 per million input tokens and $25.00 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.
Claude Opus 4.8 has a 1M context window; GLM-5.3-Flash has 1M.
Claude Opus 4.8 is a proprietary model released by Anthropic. GLM-5.3-Flash is an open weight model released by Z.ai.