Model
deepseek-r1-0528
Appears alongside
Featured in threads
Tracks
- Benchmarks & progress 2
- Safety & alignment 1
- Security & misuse 1
- Open weights & ecosystem 1
- Models & capabilities 1
US CAISI finds DeepSeek models far more jailbreak-susceptible than US frontier models
The report also found DeepSeek's most secure model was twelve times more likely than US models to follow malicious instructions hidden inside an AI agent's task.
Benchmarks & progress · Safety & alignment · Security & misuse
DeepSeek releases DeepSeek-R1-0528 update
Released under an MIT licence, the update raised AIME 2025 accuracy from 70% to 87.5% by roughly doubling the average length of the model's reasoning traces.
Open weights & ecosystem · Models & capabilities · Benchmarks & progress