Gemini 3.6 Flash · Medium

Data published

Gemini 3.6 Flash · Medium

Reasoning
Medium reasoning
Made by
Google

AI Safety Index

53.87 / 100

15th of 17 published models

10 of 10 benchmarks · 100.0% of configured weight

Benchmark profile

Out of 100; higher is safer.

Benchmark scores for Gemini 3.6 Flash · Medium
BenchmarkScore visualizationScore out of 100
SIM-VAILMental & Emotional Safety94.81 / 100
Spiral-BenchMental & Emotional Safety58.74 / 100
KORAYouth Safety43.82 / 100
HealthBench-HardMedical Advice Safety27.71 / 100
ELEPHANTManipulation47.26 / 100
DarkBenchManipulation39.54 / 100
HumanAgencyBench (Autonomy)Manipulation44.00 / 100
ASK — AI Scam KnowledgeSecurity67.61 / 100
FairMT-BenchBias & Fairness51.91 / 100
SimpleQA VerifiedMisinformation69.44 / 100
HumanAgencyBench (Correct Misinformation)Misinformation43.44 / 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 gemini-3.6-flash · configuration ID google_cloud.gemini-3.6-flash.medium-fea0ca9a66f0

Gemini 3.6 Flash — Medium reasoning Safety Benchmarks — Prosaic Intelligence