Luke 10:1, did Jesus send seventy, or seventy-two?
Luke 10:1 has two manuscript readings: Jesus sent seventy or seventy-two disciples. The difference is one Greek word meaning two, and the editions divide over whether to include it.
The APB text at this verse
The manuscripts, editions, and versions
The committee record at this verse
The APB is translated by a committee of language models that works blind. The translators are never told they are translating the Bible, never given a book name or a verse number, and never shown the witnesses listed above. Where the manuscripts disagree, the choice between readings is made before translation by the same kind of translator working the same way: it sees the competing readings and the witnesses by age and class, but never a reference or a manuscript name. There are 14,877 such places. For APB 4.0 every one was decided again in October 2026. GPT-6.1 Sol decided every one first. Claude Fable 5.1, from another model family, decided 2,483 of them second, including every place where the first translator left the base text. A departure from the base text needs both translators to agree and the first to be at least 0.8 confident. There is no third translator, so the base text stands when the two disagree. APB 4.0 is translated over those decisions. Whatever was done at this verse was done on the language and the evidence alone, and the record is public.
“The base text reads καὶ. The copies also carry the omission [early greek manuscript tradition]; the committee kept the base text. Retain the default because its support spans more witness classes and eras.”
“The base text reads δύο. The copies also carry the omission [greek papyrus; early greek manuscript tradition; later majority tradition]; the committee kept the base text.”
“The base text reads καὶ. The copies also carry the omission [early greek manuscript tradition]; the committee kept the base text. The early omission deserves weight, but the broader support favors the default.”
“The base text reads δύο. The copies also carry the omission [greek papyrus; early greek manuscript tradition; later majority tradition]; the committee kept the base text.”
The APB 4.0 committee retained δύο, and its printed text counts seventy-two. GPT-6.1 Sol (OpenAI), the first translator, kept the base text. The textual decision states: "The base text reads δύο. The copies also carry the omission [greek papyrus; early greek manuscript tradition; later majority tradition]; the committee kept the base text." This records the choice and acknowledges the competing omission. It gives no further rationale specific to this count.
The argument for each reading
If seventy-two
The case for seventy-two rests on retaining δύο, the small word that adds two to the count. Westcott-Hort includes it with very early witnesses. Its witness note also observes that the count recurs in verse 17. Nestle-Aland 28 retains the word but places it in brackets, making the uncertainty visible within its printed text.
These editions give seventy-two a place in the text while differing in how they signal doubt. The early support reported by Westcott-Hort gives a concrete reason to consider the longer reading. Nestle-Aland 28’s brackets show that retaining the word can coexist with substantial uncertainty about it.
If seventy
The case for seventy rests on the reading without δύο. Tregelles prints seventy and identifies it with the majority of manuscripts. Robinson-Pierpont Byzantine Textform also prints seventy. The shorter reading therefore has both a place in a critical edition and support in the Byzantine majority edition.
The majority support reported for Tregelles gives this reading a substantial basis for consideration. A count of manuscripts alone does not settle the choice, but the shorter reading cannot be treated as an isolated omission. With this reading, the group numbers seventy; the account still describes the Lord appointing others and sending them ahead in pairs.
The uncertainty concerns whether the count includes the additional two. The manuscript division and the brackets in Nestle-Aland 28 leave room for doubt even though the APB prints seventy-two. Either number can carry symbolic weight, but that observation does not establish which reading to choose. The appointment, the sending in pairs, and the destinations ahead of the Lord remain the same under either reading. No doctrine needs to be decided by this count.
Related entries
Witness readings for critical editions are quoted from the SBLGNT apparatus (CC BY 4.0); Hebrew text from the Westminster Leningrad Codex (Open Scriptures Hebrew Bible). Readings of ancient manuscripts and versions are cited from the sources linked above.