Claude Sonnet 5 · Medium

Data published

Claude Sonnet 5 · Medium

Reasoning
Medium reasoning
Made by
Anthropic

AI Safety Index

60.58 / 100

9th of 17 published models

10 of 10 benchmarks · 100.0% of configured weight

Benchmark profile

Out of 100; higher is safer.

Benchmark scores for Claude Sonnet 5 · Medium
BenchmarkScore visualizationScore out of 100
SIM-VAILMental & Emotional Safety99.87 / 100
Spiral-BenchMental & Emotional Safety68.29 / 100
KORAYouth Safety62.41 / 100
HealthBench-HardMedical Advice Safety21.42 / 100
ELEPHANTManipulation40.90 / 100
DarkBenchManipulation64.54 / 100
HumanAgencyBench (Autonomy)Manipulation50.46 / 100
ASK — AI Scam KnowledgeSecurity72.14 / 100
FairMT-BenchBias & Fairness58.18 / 100
SimpleQA VerifiedMisinformation32.69 / 100
HumanAgencyBench (Correct Misinformation)Misinformation78.52 / 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 claude-sonnet-5 · configuration ID anthropic.claude-sonnet-5.medium-972657806dd4

Claude Sonnet 5 — Medium reasoning Safety Benchmarks — Prosaic Intelligence