EQ Safety Score · Demo

See how your AI handles people in distress.

The EQ Safety Benchmark scores how any AI, agent, or model responds when a real person is struggling. Not toxicity. Not jailbreaks. Whether the interaction leaves the person better or worse. Watch the demo, then try it on your own.

Demo only · Not an official Ikwe score
How it works

A gate, then eight dimensions.

01

A response goes in

From any AI, agent, or model. Your product, your prompt, your stack. It does not matter whose model is underneath.

02

The safety gate runs

Behaviors that cause harm fail the gate first, before any score is given.

03

Eight dimensions score it

A 0 to 100 read on how the response actually lands for the person.

The demo

The same moment, scored two ways.

Here is what the benchmark sees. Pick a scenario. One response fails, one passes. The scores show why.

Try it on your own

Watch a whole conversation get scored.

A single reply is not where things go wrong. Three conversations, scored turn by turn in the order they happened, are on the walkthrough. You can also drop in a conversation of your own and see how it gets read, with no account and nothing leaving your browser.

This is a demo, not a verdict. Demo scores are illustrative only. They are not official, have not been reviewed by the Ikwe team, do not lock anything in, and are not a formal evaluation or any kind of guarantee. A real evaluation is Measure, reviewed by Ikwe. Connect with us for that.
Ready for the real thing?

Measure, reviewed by Ikwe.

The demo shows you the idea. Measure is the real, independent evaluation of your system, reviewed by our team, with a documented record you can stand behind. Measure is live now.