Muse Spark 1.3vsGLM-5.3
Muse Spark 1.3 | GLM-5.3 | |
|---|---|---|
| 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. | — | 743B |
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 | ||
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. | — | $1.17AkashML |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | — | $3.96AkashML |
| 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. | 75.4% | 66.9% |
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. | 88.8% | 88.2% |
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. | 49.4% | 48.2% |
GDPval-AA v2Knowledge work — economically valuable knowledge work (v2, re-based Elo) | 1754 | 1769 |
| 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. | — | 71% |
SWEAtlas CodeBase QnACodebase understanding — Questions about how an unfamiliar codebase actually works — where something is handled, what a change would touch — answered by reading the repository rather than editing it. Tests understanding rather than patch-writing. Higher is better. | 59.4% | — |
Terminal-Bench 4.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Version 4.0 recalibrated how much time, CPU and memory each task gets, removed eight tasks and fixed nineteen, so fewer runs fail for reasons that have nothing to do with the model. Scores are not comparable with earlier versions. Higher is better. | — | 41.82% |
Terminal-Bench 3.0Agentic terminal coding — command-line task completion (v3.0, much harder task set) | — | 28.3% |
JobBenchProfessional tool use — Tests the AI on professional workplace tasks that require using real work tools — the kind of multi-step jobs an office worker handles. Higher is better. | 64.9% | — |
DeepSearchQAAgentic browsing — Questions that cannot be answered from one page: the AI has to search the web, follow the trail across several sources, and put the pieces together into an answer. Higher is better. | 89.4% | — |
CyberGymCybersecurity — Tests the AI on cybersecurity challenges — finding and exploiting software weaknesses inside a safe sandbox. Higher is better. | — | 84.5% |
ExploitBenchCybersecurity — A 'capability ladder' for security research, built by CMU researchers: the AI is given known bugs in Chrome's V8 engine and scored on how far it gets toward a working exploit inside a research sandbox — from understanding the patch to triggering a crash. Higher is better. | — | 54.4% |
ExploitGym · 6-hour budgetCybersecurity — Can an AI agent turn a known software vulnerability into a working attack in a controlled lab? Built by MPI-SP researchers, the score is how many of 898 real cases (userspace programs, the V8 engine, the Linux kernel) it cracks — here with a 6-hour compute budget per case. Higher is better. | — | 130 |
ExploitGym · 2-hour budgetCybersecurity — Can an AI agent turn a known software vulnerability into a working attack in a controlled lab? Built by MPI-SP researchers, the score is how many of 898 real cases (userspace programs, the V8 engine, the Linux kernel) it cracks — here with a 2-hour compute budget per case. Higher is better. | — | 105 |
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. | — | 62.5% |
Agentic IF Index (Internal)Instruction following — Meta's internal measure of whether a model keeps following the instructions it was given while working as an agent — over a long run of tool calls, not just in a single reply. Higher is better. | 57.8% | — |
OSWorld 2.0Agentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Version 2.0 is a harder, refreshed task set. Higher is better. | 66.9% | — |
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. | — | 28.5% |
MRCR · 256k-512kLong context — Tests whether the AI can find specific details buried inside a very long document, here across inputs of roughly 256k to 512k tokens — several books' worth of text. Higher is better. | 98.5% | — |
MRCR · 512k-1MLong context — The same buried-detail retrieval test run on even longer inputs, from roughly 512k up to a million tokens. Scores usually slip as the document grows, so read it against the shorter span above. Higher is better. | 98.1% | — |
| Overview | ||
| Company | Meta | Z.ai |
| Release date | Sep 2 2026 | Aug 14 2026 |
| Access | Proprietary | Open Weight |
Other comparisons
Muse Spark 1.3vsClaude Fable 5.1GLM-5.3vsClaude Fable 5.1Muse Spark 1.3vsGPT-5.6 SolGLM-5.3vsGPT-5.6 SolMuse Spark 1.3vsGemini 3.8 FlashGLM-5.3vsGemini 3.8 FlashMuse Spark 1.3vsGrok 4.6GLM-5.3vsGrok 4.6Muse Spark 1.3vsDeepSeek-V4-Pro-0813GLM-5.3vsDeepSeek-V4-Pro-0813Muse Spark 1.3vsMistral Medium 3.5GLM-5.3vsMistral Medium 3.5
Frequently asked questions
Muse Spark 1.3 leads GLM-5.3 on 3 of the 4 benchmarks they both report (DeepSWE 1.1, Terminal-Bench 2.1, AutomationBench, GDPval-AA v2). GLM-5.3 shipped 19 days before Muse Spark 1.3, so benchmark comparisons should account for the intervening progress.
Muse Spark 1.3 is proprietary, while GLM-5.3 is open weight.
On DeepSWE 1.1, Muse Spark 1.3 leads at 75.4% vs GLM-5.3 at 66.9%. On Terminal-Bench 2.1, Muse Spark 1.3 leads at 88.8% vs GLM-5.3 at 88.2%. On AutomationBench, Muse Spark 1.3 leads at 49.4% vs GLM-5.3 at 48.2%. On GDPval-AA v2, GLM-5.3 leads at 1769 vs Muse Spark 1.3 at 1754.
Muse Spark 1.3 was released by Meta on Sep 2 2026.
GLM-5.3 was released by Z.ai on Aug 14 2026.
Muse Spark 1.3 leads on DeepSWE 1.1 — Muse Spark 1.3 75.4% vs GLM-5.3 66.9%.
Muse Spark 1.3 is a proprietary model released by Meta. GLM-5.3 is an open weight model released by Z.ai.