GLM-5.3

About

What GLM-5.3 is

GLM-5.3 GLM-5.3 uses the same base model as GLM-5.2 — every gain comes from post-training. Compared with GLM-5.2, it is much better at complex coding and long-horizon tasks: + Stronger Coding: GLM-5.3 is the most capable open-weights model for coding, with a 50% improvement over GLM-5.2 on our in-house Z.ai Code Bench. It also achieve open-source SOTA on public benchmarks including Terminal Bench 3.0 and Agents' Last Exam. + Emergent Cyber Capability: As we scaled post-training, cyber capability developed faster than we expected. GLM-5.3 is state of the art on CyberGym for vulnerability discovery, and its gains are largest further up the exploitation chain, where it more than doubles GLM-5.2 on exploitation benchmarks. Benchmark Serve GLM-5.3 Locally GLM-5.3 supports deployment with the following frameworks. Feel free to try them out: - SGLang — see cookbook - vLLM — see recipes - TokenSpeed — see here - Transformers — see transformers docs - KTransformers — see tutorial - Unsloth — see guide - For deployment on the Ascend NPU platform, inference frameworks such as vLLM-Ascend, xLLM and SGLang are supported — see here. Note - GLM-5.3 supports controlling the thinking budget through the reasoningeffort parameter, which accepts three levels: low, high, and max. It defaults to max if not passed (or if set to any other value). To use low or high, pass them explicitly. For benchmark and leaderboard reproduction, keep the default max. - In the chat template for GLM-5.3, clearthinking defaults to false if not passed. For chat scenarios, explicitly pass clearthinking=true. Footnotes - HLE w/ tools: We use sampling parameters of temperature=1.0 and topp=0.95 for evaluation, with a maximum generation length of 163,840 tokens. The evaluation is conducted with a maximum context length of 300,000 tokens, using a context management strategy. We use GPT-5.6-luna (medium) as the judge model. - NL2Repo: We evaluated NL2Repo with temperature=1.0, topp=1.0, and maxnewtokens=64k under 1M context. To prevent hacking, we use rule-based and a LLM-based judgement to prevent malicious behaviors (e.g., unauthorized pip or curl operations). - DeepSWE: We run DeepSWE using the mini-swe-age

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How language models work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys glm-5-3 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (glm-5-3 below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"glm-5-3","messages":[{"role":"user","content":"Hello"}]}'

Details

Languages, data & research

Papers

Licence

Commercial licence needed

Sources

Weights & code

Explore

More language models