GLM
GLM (General Language Model) is a large language model series developed by Zhipu AI, built on an autoregressive blank-infilling pre-training framework. The series supports natural language understanding, text generation, conversational interaction, and code writing, with bilingual Chinese-English processing capability. The GLM series encompasses versions of varying parameter scales and can be applied to question answering, summarization, reasoning, and other natural language processing tasks.
Core Facts
@ai-sdk/zai is the official Provider in the Vercel AI SDK for Zhipu AI models.
GLM unifies the pre-training objectives of natural language understanding and generation through Autoregressive Blank Infilling.
The GLM series originally adopted an autoregressive blank-filling pre-training framework that accommodates both understanding and generation capabilities.
Timeline (last 90 days)
When doing secondary processing based on a third-party open-source base, the upper limit of model capability is constrained by the base.
The course author integrated the Zhipu GLM model into Claude Code out of concern about account ban risk.
Orca's officially listed support list includes 34 agents, including Claude Code, Codex, Kimi, Qwen Code, GLM, and others.
A post published on X in August by a developer (viewed by over 40,000 people) shared a division-of-labor scheme: the most expensive model only does requirement breakdown and final acceptance, the middle coding is done by Kimi and GLM, and running tests and fixing bugs is done by Codex.
The T3 tier includes Continue, Zed, Baidu Comet, WorkBody, and GLM, defined as always having some problems in use.
Zhipu's GLM series, Meta Llama, and Alibaba Qwen all belong to the open-weight model camp.
The researchers ran this experiment with GLM 5.3, and mentioned that OpenAI's and Anthropic's models as well as open-source models such as Kimi also performed well on similar tasks.
Together has launched a Post-Training service that allows developers to post-train open-source models such as Qwen, GLM, and Kimi through custom training loops, with the platform handling the underlying infrastructure.
Together's post-training service covers major open-source model families such as Qwen, GLM, and Kimi.
inclusionAI's Ling-3.1-flash takes first place on SWE-bench_Pro (68.74), SWE-bench_Multilingual (88.5), and skillsbench (68.7), while zai-org's GLM series holds first place on evaluations such as ResearchClawBench, EvasionBench, and chi-bench.
40 more timeline events
All Facts (20)
@ai-sdk/zai is the official Provider in the Vercel AI SDK for Zhipu AI models.
90%VerifiedGLM unifies the pre-training objectives of natural language understanding and generation through Autoregressive Blank Infilling.
90%VerifiedThe GLM series originally adopted an autoregressive blank-filling pre-training framework that accommodates both understanding and generation capabilities.
90%VerifiedEarly GLM adopted Autoregressive Blank Infilling as its pre-training objective
90%VerifiedGLM系列由清华大学KEG实验室与智谱AI联合研发
90%VerifiedThe GLM series is a large language model jointly developed by Tsinghua University and Zhipu AI, built on the Autoregressive Blank Infilling training objective.
90%Verified@ai-sdk/zai depends on @ai-sdk/openai-compatible, indicating that Zhipu GLM's API interface is largely compatible with OpenAI's calling conventions.
85%VerifiedVLMs (Vision Language Models) typically consist of a visual encoder (such as ViT), a language model, and a projection layer connecting the two, with representative models including GPT-4V/4o, Claude 3.5, the LLaVA series, and InternVL
80%VerifiedGLM采用了独特的自回归填空预训练范式，与GPT的纯自回归和BERT的纯掩码语言模型都有所不同
80%VerifiedThe GLM series models from Zhipu (Z.ai) were jointly developed by Tsinghua University and Zhipu AI
75%VerifiedZhipu AI is an artificial intelligence company established through the commercialization of technology from Tsinghua University's KEG Lab.
75%VerifiedGLM uses an autoregressive blank-filling training objective, randomly masking text segments and requiring the model to autoregressively restore them.
75%VerifiedZhipu AI is a technology commercialization spinoff of Tsinghua University, and its GLM architecture adopts an autoregressive blank-filling pre-training objective.
75%VerifiedDeepSeek, Qwen, and GLM all belong to the camp of open-source models led by Chinese teams.
65%VerifiedDeepSeek Harness supports connecting to third-party providers, allowing access to models such as GLM via OpenCode Go, or connection to a local Ollama service.
65%VerifiedEnglish data accounts for an overwhelming proportion of mainstream large language model training corpora; taking public datasets such as Common Crawl as an example, English content typically constitutes 40%–60% of the total, while languages such as Vietnamese and Chinese often account for less than 5%.
65%VerifiedChatGLM is developed by Zhipu AI and is based on the GLM architecture.
65%VerifiedZhipu's GLM series models (including GLM-4 and ChatGLM) are large language models jointly developed by Tsinghua University and Zhipu AI.
65%Unverified智谱AI的GLM系列脱胎于清华大学计算机系的学术研究
90%UnverifiedDomestic models such as GLM have increased the proportion of high-quality Chinese corpus during the training phase and optimized the tokenizer design for Chinese characters.
70%