Eval directory
Evals for DeepSeek
8 evaluation packs covering adversarial robustness, safety gates, workflow quality, and operator-level checks for DeepSeek AI products.
About DeepSeek
DeepSeek is an AI company shipping frontier open-weight models (DeepSeek-V3, DeepSeek-R1) and an OpenAI-compatible API with a separate reasoner model (deepseek-reasoner), automatic disk-based context caching, function calling, JSON output, and very low token pricing. The models are released under an MIT license alongside the hosted API.
Available eval packs for DeepSeek
8 packs ready to run.
Auth Rate Limits And Cost
DeepSeek evals — Auth, Rate Limits & Cost (relift v3 InfraRed)
Chat Completions Openai Compatible
DeepSeek evals — Chat Completions (OpenAI-compatible) (relift v3 InfraRed)
Context Caching Disk Kv Cache
DeepSeek evals — Context Caching (disk KV cache) (relift v3 InfraRed)
Fim Completions Beta
DeepSeek evals — FIM / Completions (beta) (relift v3 InfraRed)
Function Calling And Tool Use
Tool SelectionDeepSeek evals — Function Calling & Tool Use (relift v3 InfraRed)
Json Structured Output
DeepSeek evals — JSON / Structured Output (relift v3 InfraRed)
Reasoning Model Deepseek Reasoner
DeepSeek evals — Reasoning Model (deepseek-reasoner) (relift v3 InfraRed)
Safety Models And Governance
DeepSeek evals — Safety, Models & Governance (relift v3 InfraRed)
Why eval DeepSeek AI
DeepSeek's AI features ship behind brand promises about accuracy, safety, and reliability. Buyers and integrators need to know those promises hold up under adversarial prompts, edge-case workflows, and the long tail of real customer inputs — not just the demo path.
The Corsac eval library for DeepSeek measures four dimensions teams care about most when deploying ai platform agents:
- Adversarial robustness — does the agent resist prompt injection, jailbreaks, and social-engineering attempts?
- Workflow quality— does it complete the task buyers were shown in the demo, on inputs that don't look like the demo?
- Safety gates — does it escalate or refuse when it should, and only then?
- Operator quality — does it preserve analyst trust by surfacing the right context at the right time?
Every eval pack above is hand-authored against DeepSeek's public product surface and runnable in Corsac with your own data.