Eval directory
Evals for Perplexity
8 evaluation packs covering adversarial robustness, safety gates, workflow quality, and operator-level checks for Perplexity AI products.
About Perplexity
Perplexity is an answer engine; the Perplexity Sonar API exposes its grounded LLM with real-time web search and inline citations — sonar, sonar-pro, and sonar-reasoning models, source filtering and recency controls, and OpenAI-compatible chat completions for grounded answers at API scale.
Available eval packs for Perplexity
8 packs ready to run.
Auth Rate Limits Tiers And Cost
Perplexity evals — Auth, Rate Limits, Tiers & Cost (relift v3 InfraRed)
Chat Completions Openai Compatible
Perplexity evals — Chat Completions (OpenAI-compatible) (relift v3 InfraRed)
Citations And Source Grounding
Answer RelevancePerplexity evals — Citations & Source Grounding (relift v3 InfraRed)
Images And Multimodal
Perplexity evals — Images & Multimodal (relift v3 InfraRed)
Reasoning Models Sonar Reasoning
Perplexity evals — Reasoning Models (Sonar Reasoning) (relift v3 InfraRed)
Safety Policy Source Quality And Governance
Perplexity evals — Safety, Policy, Source Quality & Governance (relift v3 InfraRed)
Search Controls
Perplexity evals — Search Controls (relift v3 InfraRed)
Structured Outputs And Format Controls
Perplexity evals — Structured Outputs & Format Controls (relift v3 InfraRed)
Why eval Perplexity AI
Perplexity'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 Perplexity 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 Perplexity's public product surface and runnable in Corsac with your own data.