Qwen3.8-Max-0902vsGLM-5.3-Flash
Qwen3.8-Max-0902 | 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. | 2.4T | 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 |
| 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% | 63.4% |
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% | 56.3% |
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% | 78.4% |
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% | 48.8% |
| BenchmarksPublished by one model only | ||
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 3.0Agentic terminal coding — command-line task completion (v3.0, much harder task set) | 29% | — |
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. | — | 84.3% |
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% | — |
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% | — |
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% |
GDPval-AA v2Knowledge work — economically valuable knowledge work (v2, re-based Elo) | — | 1773 |
CharXiv Reasoning · with toolsChart reasoning — The same chart-and-figure reasoning test, run with the AI allowed to use tools — writing code to inspect the image, for instance — rather than reading the chart unaided. Scores run higher than the unaided version, so read the two as separate tests. Higher is better. | — | 89.4% |
Chartography · with toolsChart tasks — A chart-centred test run with tools available to the AI, reported separately from the chart-reading benchmarks above it. Higher is better. | — | 78% |
OfficeQA ProDocument Q&A — Questions about office documents, where answering depends on reading the page as a document — layout, tables and figures included — rather than as loose text. Higher is better. | — | 62.4% |
MVBenchVideo understanding — Video questions that cannot be answered from any single frame: the AI has to follow what changes over time — the order things happen in, what moved where. Higher is better. | — | 77.8% |
MMVUVideo reasoning — Expert-level video questions drawn from specific disciplines, where answering means applying subject knowledge to what is happening on screen rather than just describing it. Higher is better. | — | 80.5% |
BabyVisionVisual reasoning — Tests core visual reasoning — seeing and understanding images the way even young children can, which AIs often find surprisingly hard. Higher is better. | — | 53.4% |
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 26 2026 |
| Access | Proprietary | Open Weight |
Other comparisons
Qwen3.8-Max-0902vsClaude Fable 5.1GLM-5.3-FlashvsClaude Fable 5.1Qwen3.8-Max-0902vsGPT-5.6 SolGLM-5.3-FlashvsGPT-5.6 SolQwen3.8-Max-0902vsGemini 3.7 FlashGLM-5.3-FlashvsGemini 3.7 FlashQwen3.8-Max-0902vsMuse GlimmerGLM-5.3-FlashvsMuse GlimmerQwen3.8-Max-0902vsGrok 4.6GLM-5.3-FlashvsGrok 4.6Qwen3.8-Max-0902vsDeepSeek-V4-Pro-0813GLM-5.3-FlashvsDeepSeek-V4-Pro-0813
Frequently asked questions
Qwen3.8-Max-0902 leads GLM-5.3-Flash on 3 of the 4 benchmarks they both report (DeepSWE 1.1, NL2Repo-Bench, Toolathlon-Verified, AutomationBench). GLM-5.3-Flash shipped 7 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-Flash has 320B. Context windows are 1M (Qwen3.8-Max-0902) vs 1M (GLM-5.3-Flash). Qwen3.8-Max-0902 is proprietary, while GLM-5.3-Flash is open weight.
On DeepSWE 1.1, Qwen3.8-Max-0902 leads at 69.3% vs GLM-5.3-Flash at 63.4%. On NL2Repo-Bench, Qwen3.8-Max-0902 leads at 64.9% vs GLM-5.3-Flash at 56.3%. On Toolathlon-Verified, GLM-5.3-Flash leads at 78.4% vs Qwen3.8-Max-0902 at 73.3%. On AutomationBench, Qwen3.8-Max-0902 leads at 50.8% vs GLM-5.3-Flash at 48.8%.
Qwen3.8-Max-0902 was released by Qwen on Sep 2 2026.
GLM-5.3-Flash was released by Z.ai on Aug 26 2026.
Qwen3.8-Max-0902 leads on DeepSWE 1.1 — Qwen3.8-Max-0902 69.3% vs GLM-5.3-Flash 63.4%.
Qwen3.8-Max-0902 has a 1M context window; GLM-5.3-Flash has 1M.
Qwen3.8-Max-0902 is a proprietary model released by Qwen. GLM-5.3-Flash is an open weight model released by Z.ai.