Composer 2vsGLM-4.7
Composer 2 | GLM-4.7 | |
|---|---|---|
| Specifications | ||
Context window | — | 128k |
| Benchmarks | ||
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. | — | 73.8% |
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 v3.1Cursor's own test of harder, real-world coding tasks inside a code editor. Higher is better. | 52.2% | — |
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% | — |
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%Best | 41% |
Web browsing BrowseCompCan the AI browse the web and track down hard-to-find answers? Higher is better. | — | 52% |
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. | — | 24.8% |
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. | — | 42.8% |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 85.7% |
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. | — | 1433 |
| Overview | ||
| Company | SpaceXAI | Z.ai |
| Release date | Mar 19 2026 | Dec 22 2025 |
| Access | Proprietary | Open Weight |
Which is better: Composer 2 or GLM-4.7?
Composer 2 leads GLM-4.7 on 1 of the 1 benchmark they both report (Terminal-Bench 2.0). GLM-4.7 shipped 87 days before Composer 2, so benchmark comparisons should account for the intervening progress.
Composer 2 is proprietary, while GLM-4.7 is open weight.
On Terminal-Bench 2.0, Composer 2 leads at 61.7% vs GLM-4.7 at 41%.
Frequently asked questions
Composer 2 was released by SpaceXAI on Mar 19 2026.
GLM-4.7 was released by Z.ai on Dec 22 2025.
Composer 2 leads on Terminal-Bench 2.0 — Composer 2 61.7% vs GLM-4.7 41%.
Composer 2 is a proprietary model released by SpaceXAI. GLM-4.7 is an open weight model released by Z.ai.
Other comparisons
Composer 2vsClaude Opus 5GLM-4.7vsClaude Opus 5Composer 2vsGPT-5.6-CyberGLM-4.7vsGPT-5.6-CyberComposer 2vsGemini 3.7 FlashGLM-4.7vsGemini 3.7 FlashComposer 2vsMuse GlimmerGLM-4.7vsMuse GlimmerComposer 2vsDeepSeek-V4-Pro-0813GLM-4.7vsDeepSeek-V4-Pro-0813Composer 2vsMistral Medium 3.5GLM-4.7vsMistral Medium 3.5