Our Data

An open evaluation of name-to-gender inference

We evaluate Genderize against public datasets in which each person's gender is already recorded, reporting accuracy and coverage for every set. Each individual prediction — correct, incorrect, or no prediction — is listed below, so the aggregate figures can be checked and reproduced.

Results

Per-dataset accuracy, and every prediction behind it

Every prediction sits next to the person's real gender, so you can check the numbers yourself.

Choose a dataset 2

Public datasets with a recorded gender for every person, scored with the person's country known.

More datasets added over time.

Showing 51–75 of 88,153

Name	Country	True gender	Predicted	Probability	Result
Aas Mmmdov	Türkiye	male	male	98.4%	Correct
Aauri Lorena Bokesa Abia	Spain	female	female	80.3%	Correct
Aavo Pikkuus	Russia	male	male	94.7%	Correct
Ababel Yeshaneh Birhane	Ethiopia	female	male	69.0%	Incorrect
Abadi Hadis Embaye	Ethiopia	male	male	84.5%	Correct
Abas Ismaili	Iran	male	male	99.5%	Correct
Abbas Al-Harbi	Kuwait	male	male	99.5%	Correct
Abbas Al-Qaisoum	Saudi Arabia	male	male	98.3%	Correct
Abbas Dabbaghi Souraki	Iran	male	male	99.9%	Correct
Abbas Fallah	Iran	male	male	99.6%	Correct
Abbas Haj Kenari	Iran	male	male	99.8%	Correct
Abbas Jadidi	Iran	male	male	99.6%	Correct
Abbas Mohamed	Nigeria	male	male	99.0%	Correct
Abbas Qali	—	male	male	97.7%	Correct
Abbas Saeidi Tanha	Iran	male	male	99.7%	Correct
Abbas Samimi	Iran	male	male	99.6%	Correct
Abbas Talebi	Iran	male	male	99.7%	Correct
Abbey Weitzeil	United States	female	female	99.4%	Correct
Abbo Dias Bartolomeu	Angola	male	male	99.2%	Correct
Abbos Atayev	Uzbekistan	male	male	100.0%	Correct
Abbos Rakhmonov	Uzbekistan	male	male	100.0%	Correct
Abbubaker Mobara	South Africa	male	male	84.0%	Correct
Abby Bishop	Australia	female	female	100.0%	Correct
Abby May Erceg	New Zealand	female	female	99.7%	Correct
Abclvio Rodrigues	Brazil	male	male	95.9%	Correct

Method

How we measured this

Population. We score the "alive-today" set: people with a known birth year, at most 80 years old.

Accuracy is the share of returned predictions that matched the known gender. Coverage is the share of people we returned any prediction for — we abstain when there's too little signal, and those show as "no prediction".

Country context. Every prediction here is made with the person's country known — the mode most API users run, and the most accurate one.

Rounding. Figures are the exact measured value to two decimals — we never round accuracy up.