Five language tiers show how many solutions qualify and whether any qualifying solution is one-step.

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

For Standard, a simple solution and a backup meet tone of voice, tags and formatting on their own in 39 or 40 of the 40 languages of tier 2, and general translation quality in 16 of them. In those 16, only two-step or three-step solutions meet all the requirements at once.

Of the 29 languages of tiers 3 and 4 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, the tier chart and the table of errors, cost and time, EPT means total errors per 1,000 source words across all requirements. It adds the weighted general translation quality errors (minor 1, major 5, critical 10, as in the quality bar), missed glossary terms, sentences in the wrong register, tag errors and sentences that fail gender neutrality. Each error of the other requirements counts once, and the same error types are included at every quality level.

For each requirement, we calculate the count by multiplying the share that failed by the number of terms, sentences or tags checked across the four texts. We then express the total per 1,000 source words. Formatting pass/fail results affect whether a solution qualifies but do not add to EPT.