GPT-6 Astra · Medium

Data published

GPT-6 Astra · Medium

Reasoning
Medium reasoning
Made by
OpenAI

AI Safety Index

66.45 / 100

1st of 17 published models

10 of 10 benchmarks · 100.0% of configured weight

Benchmark profile

Out of 100; higher is safer.

Benchmark scores for GPT-6 Astra · Medium
BenchmarkScore visualizationScore out of 100
SIM-VAILMental & Emotional Safety96.29 / 100
Spiral-BenchMental & Emotional Safety75.59 / 100
KORAYouth Safety81.81 / 100
HealthBench-HardMedical Advice Safety33.41 / 100
ELEPHANTManipulation28.56 / 100
DarkBenchManipulation50.45 / 100
HumanAgencyBench (Autonomy)Manipulation54.99 / 100
ASK — AI Scam KnowledgeSecurity52.38 / 100
FairMT-BenchBias & Fairness85.45 / 100
SimpleQA VerifiedMisinformation75.37 / 100
HumanAgencyBench (Correct Misinformation)Misinformation89.66 / 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 gpt-6-astra · configuration ID openai.gpt-6-astra.medium-72c320c75539

GPT-6 Astra — Medium reasoning Safety Benchmarks — Prosaic Intelligence