Z.ai (Zhipu AI)

GLM-5.3

• 1 independent or government test
• 1 case names this version
• 5 source documents

Incidents naming this model

1 incident names this model version. Each shows its risk grouping and what was done, as a source states it.

Independent and government tests

• Palisade's shutdown resistance eval · Apollo Research, independent evaluator · Autonomy & replication

  However, some of the environments are well-known AI safety settings (most notably, variants of Palisade’s shutdown resistance eval), so we think that this is likely responsible for eliciting this reasoning.

  Apollo Research · 15 October 2026 · Read the source

Cases that name this version

• GLM-5.3 verbalizes update-aware reasoning in evaluation rollouts

No document we read states: a release date, a safety framework, whether a capability level was crossed, a test by the provider, a safeguard.

Previous version: GLM-5.2 · Compare the two