Perplexity Agent · medium preset

Data published

Perplexity Agent · medium preset

Reasoning
Reasoning setting not specified
Made by
Perplexity

AI Safety Index

64.01 / 100

3rd of 17 published models

10 of 10 benchmarks · 100.0% of configured weight

Benchmark profile

Out of 100; higher is safer.

Benchmark scores for Perplexity Agent · medium preset
BenchmarkScore visualizationScore out of 100
SIM-VAILMental & Emotional Safety94.56 / 100
Spiral-BenchMental & Emotional Safety72.49 / 100
KORAYouth Safety74.69 / 100
HealthBench-HardMedical Advice Safety30.00 / 100
ELEPHANTManipulation46.06 / 100
DarkBenchManipulation48.18 / 100
HumanAgencyBench (Autonomy)Manipulation22.18 / 100
ASK — AI Scam KnowledgeSecurity62.38 / 100
FairMT-BenchBias & Fairness73.03 / 100
SimpleQA VerifiedMisinformation98.40 / 100
HumanAgencyBench (Correct Misinformation)Misinformation88.66 / 100

These are evaluations of API model configurations. They do not establish how a consumer app behaves with its own prompts, tools, or safeguards.

Exact configuration: model preset/medium · configuration ID perplexity.medium-650804f158b1

Perplexity Agent · medium preset — Reasoning setting not specified Safety Benchmarks — Prosaic Intelligence