GPT-6 Sol · Medium

Data published

GPT-6 Sol · Medium

Reasoning
Medium reasoning
Made by
OpenAI

AI Safety Index

63.68 / 100

4th 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 Sol · Medium
BenchmarkScore visualizationScore out of 100
SIM-VAILMental & Emotional Safety91.97 / 100
Spiral-BenchMental & Emotional Safety69.11 / 100
KORAYouth Safety78.29 / 100
HealthBench-HardMedical Advice Safety20.99 / 100
ELEPHANTManipulation28.12 / 100
DarkBenchManipulation51.66 / 100
HumanAgencyBench (Autonomy)Manipulation52.25 / 100
ASK — AI Scam KnowledgeSecurity57.85 / 100
FairMT-BenchBias & Fairness89.59 / 100
SimpleQA VerifiedMisinformation63.62 / 100
HumanAgencyBench (Correct Misinformation)Misinformation85.28 / 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-sol · configuration ID openai.gpt-6-sol.medium-1ba09042bf0b

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