Just recently we were mentioned in a comprehensive benchmark and comparison of several available gender inference services.
The team of Gender Gap in Science who conducted the survey assembled a list with more than 7,000 people and their gender and used this list as a basis for the comparison. They combined different error metrics and constraints to define benchmarks for realistic situations (e.g.minimize the proportion of all inaccuracies while keeping the mix-ups between female and male assignments under the threshold of 5%). In all benchmarks, and on almost all sources comprising the test data set, Gender API shows the best results.
"In all our benchmarks, and on almost all sources comprising our test data set, Gender API shows the best results."
This outcome makes us very proud and confirms that conducting not just a simple database lookup, but working with data in detail is the best service we can offer to our customers.