Qwen3.8-Max-0902vsGLM-5.3
Qwen3.8-Max-0902 | 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. | 2.4T | 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. | — | $1.1875Io Net |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | — | $3.96Friendli |
| 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. | 69.3% | 66.9% |
Terminal-Bench 3.0Agentic terminal coding — command-line task completion (v3.0, much harder task set) | 29% | 28.3% |
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. | 50.8% | 48.2% |
| 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% |
NL2Repo-BenchRepo-level code generation — Tests whether the AI can turn a natural-language requirement into working code across an entire repository, not just produce a single function or patch. Higher is better. | 64.9% | — |
QwenSWEBench V2Software engineering — Qwen's in-house coding benchmark, second version, built around complex real-world software-engineering tasks. Scores are not comparable with the first version. Higher is better. | 70% | — |
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 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. | — | 88.2% |
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% | — |
CoWorkBenchLong-horizon office work — Tests long-running office tasks across fields including computer science, finance, law, medicine, and other productivity work. Higher is better. | 76.1% | — |
Toolathlon-VerifiedPersonal tool use — Tests how well the AI uses everyday personal tools and apps to get things done — a human-checked version of Toolathlon. Higher is better. | 73.3% | — |
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% |
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% |
GDPval-AA v2Knowledge work — economically valuable knowledge work (v2, re-based Elo) | — | 1769 |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | 82.7% | — |
| Overview | ||
| Company | Qwen | Z.ai |
| Release date | Sep 2 2026 | Aug 14 2026 |
| Access | Proprietary | Open Weight |
Other comparisons
Qwen3.8-Max-0902vsClaude Fable 5.1GLM-5.3vsClaude Fable 5.1Qwen3.8-Max-0902vsGPT-5.6 SolGLM-5.3vsGPT-5.6 SolQwen3.8-Max-0902vsGemini 3.7 FlashGLM-5.3vsGemini 3.7 FlashQwen3.8-Max-0902vsMuse GlimmerGLM-5.3vsMuse GlimmerQwen3.8-Max-0902vsGrok 4.6GLM-5.3vsGrok 4.6Qwen3.8-Max-0902vsDeepSeek-V4-Pro-0813GLM-5.3vsDeepSeek-V4-Pro-0813
Frequently asked questions
Qwen3.8-Max-0902 leads GLM-5.3 on 3 of the 3 benchmarks they both report (DeepSWE 1.1, Terminal-Bench 3.0, AutomationBench). GLM-5.3 shipped 19 days before Qwen3.8-Max-0902, so benchmark comparisons should account for the intervening progress.
Qwen3.8-Max-0902 has 2.4T parameters, while GLM-5.3 has 743B. Qwen3.8-Max-0902 is proprietary, while GLM-5.3 is open weight.
On DeepSWE 1.1, Qwen3.8-Max-0902 leads at 69.3% vs GLM-5.3 at 66.9%. On Terminal-Bench 3.0, Qwen3.8-Max-0902 leads at 29% vs GLM-5.3 at 28.3%. On AutomationBench, Qwen3.8-Max-0902 leads at 50.8% vs GLM-5.3 at 48.2%.
Qwen3.8-Max-0902 was released by Qwen on Sep 2 2026.
GLM-5.3 was released by Z.ai on Aug 14 2026.
Qwen3.8-Max-0902 leads on DeepSWE 1.1 — Qwen3.8-Max-0902 69.3% vs GLM-5.3 66.9%.
Qwen3.8-Max-0902 is a proprietary model released by Qwen. GLM-5.3 is an open weight model released by Z.ai.