DeepSeek V4 Pro 0813

Named by 2 kept items in this workspace.

1 items name it under affected products and 1 under tools.

The items that name it 2

EvoRiskBench: An Evolving Benchmark for Runtime Security Risks in Workspace Agents
paperas affected products2026-10-02It is written here as DeepSeek-V4-Pro-0813.
We burned 11.7bn tokens to find the best cyber AI model
articleas tools2026-08-21
AI model benchmarked for rediscovering vulnerabilities from source code; found most vulnerabilities pooled (28/32), 17 on first pass, median 24 of 30 turns, cost about $295 for three runs

In every workspace you can read 4

AI

Welcome Le Chonk: Mistral Large 4 on Hugging Face
article2026-10-29
Introducing Mistral Large 4 ("Le Chonk")
article2026-10-06

Security

EvoRiskBench: An Evolving Benchmark for Runtime Security Risks in Workspace Agents
paper2026-10-02It is written here as DeepSeek-V4-Pro-0813.
We burned 11.7bn tokens to find the best cyber AI model
article2026-08-21

All technologies in this workspace.