Qwen3.5vsGLM-5.2
Qwen3.5 | GLM-5.2 | |
|---|---|---|
| Specifications | ||
Parameters | 397B | 744B |
Context window | 1M | 1M |
| Benchmarks | ||
Nonsense detection BullshitBench v2Given 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. | — | 31% |
Agentic coding SWE-Bench ProCan 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. | — | 62.1% |
Coding SWE-Bench VerifiedReal 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. | 76.4% | — |
Multilingual coding SWE-Bench MultilingualLike SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | 69.3% | — |
Agentic coding CursorBench v3.2Cursor's own test of harder, real-world coding tasks inside a code editor, on the refreshed v3.2 task set. Scores aren't comparable with v3.1. Higher is better. | — | 55% |
Agentic coding CursorBench v3.1Cursor's own test of harder, real-world coding tasks inside a code editor. Higher is better. | — | 54.6% |
Agentic coding DeepSWE 1.1Artificial 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. | — | 44% |
Next.js coding Next.js EvalsVercel'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% |
Agentic computer work Frontier-Bench v0.1A 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. | — | 5.1% |
Agentic terminal coding Terminal-Bench 2.1Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | — | 81% |
Agentic terminal coding Terminal-Bench 2.0Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. | 52.5% | — |
Web browsing BrowseCompCan the AI browse the web and track down hard-to-find answers? Higher is better. | 69% | — |
Multidisciplinary reasoning Humanity's Last Exam · no toolsHumanity'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. | 28.7% | 40.5%Best |
Multidisciplinary reasoning Humanity's Last Exam · with toolsHumanity'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. | — | 54.7% |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 88.4% | 91.2%Best |
Agentic computer use OSWorld-VerifiedCan the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | 62.2% | — |
Knowledge work GDPval-AA v2economically valuable knowledge work (v2, re-based Elo) | — | 1514 |
Chart reasoning CharXiv ReasoningCan the AI read and reason about complex charts and figures, not just text? Higher is better. | 80.8% | — |
Multimodal reasoning MMMU-ProA tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | 79% | — |
Multimodal MMMUTests the AI on understanding images and text together across many college subjects. Higher is better. | 85% | — |
Community preference (code) Arena Elo (Code)Like the text arena, but people vote on which AI writes better code. The votes become a chess-style Elo rating on arena.ai. Higher is better. | — | 1587 |
| Overview | ||
| Company | Qwen | Z.ai |
| Release date | Feb 16 2026 | Jun 16 2026 |
| Access | Open Weight | Open Weight |
Which is better: Qwen3.5 or GLM-5.2?
GLM-5.2 leads Qwen3.5 on 2 of the 2 benchmarks they both report (Humanity's Last Exam, GPQA Diamond). Qwen3.5 shipped 120 days before GLM-5.2, so benchmark comparisons should account for the intervening progress.
Qwen3.5 has 397B parameters, while GLM-5.2 has 744B. Context windows are 1M (Qwen3.5) vs 1M (GLM-5.2).
On Humanity's Last Exam · no tools, GLM-5.2 leads at 40.5% vs Qwen3.5 at 28.7%. On GPQA Diamond, GLM-5.2 leads at 91.2% vs Qwen3.5 at 88.4%.
Frequently asked questions
Qwen3.5 was released by Qwen on Feb 16 2026.
GLM-5.2 was released by Z.ai on Jun 16 2026.
GLM-5.2 leads on Humanity's Last Exam · no tools — Qwen3.5 28.7% vs GLM-5.2 40.5%.
Qwen3.5 has a 1M context window; GLM-5.2 has 1M.