Composer 2vsGLM-5.2
Composer 2 | GLM-5.2 | |
|---|---|---|
| Specifications | ||
Parameters | — | 744B |
Context window | — | 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% |
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. | 73.7% | — |
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. | 52.2% | 54.6%Best |
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. | 75% | 88%Best |
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. | 61.7% | — |
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. | — | 40.5% |
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. | — | 91.2% |
Knowledge work GDPval-AA v2economically valuable knowledge work (v2, re-based Elo) | — | 1514 |
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 | SpaceXAI | Z.ai |
| Release date | Mar 19 2026 | Jun 16 2026 |
| Access | Proprietary | Open Weight |
Which is better: Composer 2 or GLM-5.2?
GLM-5.2 leads Composer 2 on 2 of the 2 benchmarks they both report (CursorBench v3.1, Next.js Evals). Composer 2 shipped 89 days before GLM-5.2, so benchmark comparisons should account for the intervening progress.
Composer 2 is proprietary, while GLM-5.2 is open weight.
On CursorBench v3.1, GLM-5.2 leads at 54.6% vs Composer 2 at 52.2%. On Next.js Evals, GLM-5.2 leads at 88% vs Composer 2 at 75%.
Frequently asked questions
Composer 2 was released by SpaceXAI on Mar 19 2026.
GLM-5.2 was released by Z.ai on Jun 16 2026.
GLM-5.2 leads on CursorBench v3.1 — Composer 2 52.2% vs GLM-5.2 54.6%.
Composer 2 is a proprietary model released by SpaceXAI. GLM-5.2 is an open weight model released by Z.ai.
Other comparisons
Composer 2vsClaude Opus 5GLM-5.2vsClaude Opus 5Composer 2vsGPT-5.6-CyberGLM-5.2vsGPT-5.6-CyberComposer 2vsGemini 3.7 FlashGLM-5.2vsGemini 3.7 FlashComposer 2vsMuse GlimmerGLM-5.2vsMuse GlimmerComposer 2vsDeepSeek-V4-Pro-0813GLM-5.2vsDeepSeek-V4-Pro-0813Composer 2vsMistral Medium 3.5GLM-5.2vsMistral Medium 3.5