Lab system cards and frameworks · Model card · Google DeepMind
Gemini 2.5 Pro Model Card
Read at storage.googleapis.com ↗Read at sourceAll rights reserved
Outline · 21 pages
- Model Informationp. 2
- Model Datap. 3
- Implementation and Sustainabilityp. 3
- Evaluationp. 4
- Intended Usage and Limitationsp. 7
- Ethics and Safetyp. 7
- Frontier Safety Critical Capability Evaluationsp. 10
- CBRNp. 12
- Cybersecurityp. 14
- Machine Learning R&Dp. 17
- Deceptive Alignmentp. 19
- Frontier Safety: Summaryp. 20
- Appendix: Frontier Safety Correctness Testsp. 21