We assign four language tiers based on whether two solutions meet the requirements and how many steps they need.

For Basic, the tiers follow general translation quality, the only requirement of the level.

For Standard, two one-step solutions meet tone of voice, tags and formatting on their own in 57 or 58 of the 58 languages of tier 2, and general translation quality in 21 of them. In those 21, fewer than two one-step solutions meet all the requirements at once.

Of the 29 languages of tier 3 for Advanced, 25 have fewer than two gender-neutral best solutions even with the gender-neutrality agent. In Afrikaans, Burmese, Portuguese (European) and Sundanese, the gender-neutral versions miss other requirements.

In the explorer, EPT counts the errors of every requirement, each error once. To the general translation quality errors (critical, major and minor), it adds the missed glossary terms, the sentences in the wrong register, the tag errors and the sentences that miss gender neutrality, per 1,000 source words of the four texts, at every quality level. Each count is the share missed times the number of terms, sentences or tags checked in the four texts. Formatting is a requirement a text meets or misses as a whole, so it decides only whether a solution meets a quality level. The tier chart and the table of errors, cost and time per tier count the general translation quality errors only.