Qwen3.8-Flash-NextvsGLM-5.3
Qwen3.8-Flash-Next | 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. | 125B | 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. | 262k | — |
| 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. | — | $1.40Z.AI |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | — | $4.40Z.AI |
| 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. | 58.7% | 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. | 24.3% | 28.5% |
| 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% |
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. | 62.5% | — |
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. | 81% | — |
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. | 48.1% | — |
LiveCodeBenchCompetitive coding — Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | 91.9% | — |
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. | 55.7% | — |
CoWorkBenchLong-horizon office work — Tests long-running office tasks across fields including computer science, finance, law, medicine, and other productivity work. Higher is better. | 73.9% | — |
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. | 73.5% | — |
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 · 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. | 35.9% | — |
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% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 91.7% | — |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | 81.3% | — |
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. | 19.4% | — |
Agent's Last Exam · scoreAgentic computer use — The graded score on the same desktop and operating-system tasks in Agent's Last Exam, giving partial credit for progress beyond the strict pass-or-fail result. Higher is better. | 51.2% | — |
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. | — | 48.2% |
GDPval-AA v2Knowledge work — economically valuable knowledge work (v2, re-based Elo) | — | 1769 |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | 84.6% | — |
LVBenchVideo understanding — Can the AI follow a very long video — up to an hour — and answer questions that need details from far apart in it? Higher is better. | 76.6% | — |
| Overview | ||
| Company | Qwen | Z.ai |
| Release date | Aug 26 2026 | Aug 14 2026 |
| Access | Open Weight | Proprietary |
Other comparisons
Qwen3.8-Flash-NextvsClaude Opus 5GLM-5.3vsClaude Opus 5Qwen3.8-Flash-NextvsGPT-5.6 SolGLM-5.3vsGPT-5.6 SolQwen3.8-Flash-NextvsGemini 3.7 FlashGLM-5.3vsGemini 3.7 FlashQwen3.8-Flash-NextvsMuse GlimmerGLM-5.3vsMuse GlimmerQwen3.8-Flash-NextvsGrok 4.6GLM-5.3vsGrok 4.6Qwen3.8-Flash-NextvsDeepSeek-V4-Pro-0813GLM-5.3vsDeepSeek-V4-Pro-0813
Frequently asked questions
GLM-5.3 leads Qwen3.8-Flash-Next on 2 of the 2 benchmarks they both report (DeepSWE 1.1, Agent's Last Exam). GLM-5.3 shipped 12 days before Qwen3.8-Flash-Next, so benchmark comparisons should account for the intervening progress.
Qwen3.8-Flash-Next has 125B parameters, while GLM-5.3 has 743B. Qwen3.8-Flash-Next is open weight, while GLM-5.3 is proprietary.
On DeepSWE 1.1, GLM-5.3 leads at 66.9% vs Qwen3.8-Flash-Next at 58.7%. On Agent's Last Exam · pass@1, GLM-5.3 leads at 28.5% vs Qwen3.8-Flash-Next at 24.3%.
Qwen3.8-Flash-Next was released by Qwen on Aug 26 2026.
GLM-5.3 was released by Z.ai on Aug 14 2026.
GLM-5.3 leads on DeepSWE 1.1 — Qwen3.8-Flash-Next 58.7% vs GLM-5.3 66.9%.
Qwen3.8-Flash-Next is an open weight model released by Qwen. GLM-5.3 is a proprietary model released by Z.ai.