Z.ai (Zhipu AI)
Z.ai (Zhipu AI) has 7 model versions on record; 2 have at least one documented fact.
Of the 2 versions listed below, 1 documents tests by an independent or government party. None documents a published framework, threshold determinations, tests the provider ran itself, safeguards the provider describes.
Model versions with documented facts
| Model | What is documented |
|---|---|
| GLM-5.3 · 5 documents | |
| GLM-5.2 · 4 documents |
No document we read states a capability level, a test or a safeguard for: GLM-5.3-Flash, GLM-5V-Turbo, GLM-4.7-Flash. GLM-5.1, GLM-5: their documents report tests only as table rows or lines that do not name the version on their own; each page links the documents.
Each test and safeguard, by who documents it
For each item, how many of the 2 versions listed above whose documents we read in full have it from an outside party (an independent or government tester), from the provider, or as a claim we could not confirm.
- Tested: chemical, biological, radiological, nuclear (Testing): outside party 1
- Tested: cyber capabilities (Testing): outside party 1
- Tested: autonomy and replication (Testing): outside party 1
- Tested: deception and sabotage (Testing): outside party 1
- Tested: misuse and jailbreak (Testing): outside party 1
No document we read states, for any of these versions: Published framework with capability thresholds; Threshold determination for this release; Serious-incident disclosure commitment; Pre-release external access; Tested: harmful content; Tested: injection and agentic risks; Tested: bias; Tested: privacy; Safety training (harmlessness and refusal); Agent permission limits and sandboxing; Human approval for high-risk actions; Misuse monitoring and enforcement; Reasoning (chain-of-thought) monitoring; Staged or restricted access; Output provenance and watermarking; Telemetry and audit logging; Domain-specific safeguards (CBRN or cyber); Vulnerability disclosure and bug-bounty programme; Third-party or government red-team access during development.