The model card explicitly separates Ethics and Content Safety from Frontier Safety; self-harm is present only as dangerous-content treatment, not as a frontier threshold domain. Publication date is coded at month precision because the source states only Model card update: December, 2025.
Contents
Summary
Gemini 3 Pro - Model Card is a model card from Google DeepMind dated December 2025. The model card explicitly separates Ethics and Content Safety from Frontier Safety; self-harm is present only as dangerous-content treatment, not as a frontier threshold domain. Publication date is coded at month precision because the source states only Model card update: December, 2025.
Representation
This document codes self-harm as proxy domain with evaluative-object status proxy_represented. The public crosswalk records self-harm naming as explicit and mechanism coverage as GEN; DET; JB.
| Field | Value |
|---|---|
| Organization | Google DeepMind |
| Document type | model_card |
| Document genre | product_safety_artifact |
| Risk status | Class III |
| First-class equivalence | no |
| Threshold mechanism | none |
| Deployment consequence | none |
| Multi-turn evaluation | partial |
Assessment
The retained crosswalk places this document at Class III. That classification reflects what the document itself operationalizes publicly, not the organization's overall internal practice.
Related pages
Use the linked provider, methods, and neighboring governance pages below to place this document in context.
- Google and Google DeepMind
- Coding Rules
- Source Selection
- ANTHROPIC-2025-01
- GOOGLE-2024-01
- GOOGLEDEEPMIND-2025-01
Sources
The primary public source for this page is https://deepmind.google/models/model-cards/gemini-3-pro. The coded evidence excerpt is: Dangerous content (e.g., promoting suicide, or instructing in activities that could cause real-world harm)..
This page is grounded in the DOI policy registry, the policy coding manual, and the document's own public URL.
Access publication
Safety note
This publication preserves a harm-minimization posture and does not provide self-harm instructions. If you or someone you know is in immediate danger, call your local emergency number. In the U.S. and Canada, call or text 988.