Composer 2.5vsGLM-5.1
Composer 2.5 | GLM-5.1 | |
|---|---|---|
| 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. | — | 744B |
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. | — | 200k |
| API pricingUSD per 1M tokens · lower wins | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | — | $1.40 |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | — | $4.40 |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | — | $0.26 |
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. | — | $0.9646Baidu |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | — | $3.0316Baidu |
| Benchmarks | ||
Next.js EvalsNext.js coding — Vercel'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. | 81% | 58% |
Terminal-Bench 2.0Agentic terminal coding — Can 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. | 69.3% | 63.5% |
| 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. | — | 22% |
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. | 54% | — |
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. | 79.8% | — |
DeepSWE 1.0Agentic 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. Higher is better. | 18% | — |
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. | 73% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 68% |
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. | — | 52.3% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 86.2% |
threejsevalCommunity preference (Three.js) — Every model gets the same prompt — "the Eiffel Tower", "a glass fishbowl", "a robot arm picking toys into a box" — and builds a 3D scene in Three.js. Real people then see two scenes side by side, names hidden, and vote for the one they prefer. The votes become a chess-style Elo rating on threejseval.com, averaged across all the prompts. It measures whether the scene looks and moves right to a human eye, not whether the code passes a test. Higher is better. | 1120 | — |
| Overview | ||
| Company | SpaceXAI | Z.ai |
| Release date | May 18 2026 | Apr 7 2026 |
| Access | Proprietary | Open Weight |
Other comparisons
Composer 2.5vsClaude Fable 5.1GLM-5.1vsClaude Fable 5.1Composer 2.5vsGPT-6 AstraGLM-5.1vsGPT-6 AstraComposer 2.5vsGemini 3.8 FlashGLM-5.1vsGemini 3.8 FlashComposer 2.5vsMuse Spark 1.3GLM-5.1vsMuse Spark 1.3Composer 2.5vsDeepSeek-V4.1-FlashGLM-5.1vsDeepSeek-V4.1-FlashComposer 2.5vsMistral Medium 3.5GLM-5.1vsMistral Medium 3.5
Frequently asked questions
Composer 2.5 leads GLM-5.1 on 2 of the 2 benchmarks they both report (Next.js Evals, Terminal-Bench 2.0). Only GLM-5.1 has a verified first-party API price: $1.40 per million input tokens and $4.40 per million output tokens. No pay-as-you-go API rate is tracked for Composer 2.5. GLM-5.1 shipped 41 days before Composer 2.5, so benchmark comparisons should account for the intervening progress.
Composer 2.5 is proprietary, while GLM-5.1 is open weight.
On Next.js Evals, Composer 2.5 leads at 81% vs GLM-5.1 at 58%. On Terminal-Bench 2.0, Composer 2.5 leads at 69.3% vs GLM-5.1 at 63.5%.