What it measures

Multilingual translation is evaluated across languages and translation directions. Read automatic metric scores alongside the exact language coverage and text or speech input route.

Reading the measurement

Accuracy is only part of the picture. Inspect unsupported answers, abstentions, language coverage and the evidence available to the model. A confident response can still be wrong, and a broad average can hide a specialist gap.

Published evaluation

chrF++ averaged across the 95-language directions shared by the compared systems. This is text-to-text translation on FLORES, not speech translation on FLEURS, and not WMT24. Source model sizes and direction remain explicit.

Where this fits in an evaluation suite

Read accuracy together with error and abstention rates. Domain averages can hide language gaps, specialist failures, and poorly calibrated confidence.

Start with a capability hypothesis, then choose a second test with a different failure mode. Keep the checkpoint, reasoning effort, agent tools, sampling policy, and scoring procedure fixed when measuring a training intervention. Record failures and missing outputs in the denominator.

A reproducible comparison

chrF++ averaged across the 95-language directions shared by the compared systems. This is text-to-text translation on FLORES, not speech translation on FLEURS, and not WMT24. Source model sizes and direction remain explicit.

Publish the exact run configuration, item coverage, score units, and available uncertainty. If a source supplies only an aggregate or a single run, preserve that limit. A new model name or a rounded score alone does not establish a capability improvement.

PRIMARY EVIDENCE & FURTHER READING

  1. SeamlessM4T: Massively Multilingual & Multimodal Machine Translation — published result table ↗

    Communication, Seamless, Barrault, Loïc, Chung, Yu-An, Meglioli, Mariano Cora, Dale, David, Dong, Ning et al. · 2023

    All 68 authors

    Communication, Seamless, Barrault, Loïc, Chung, Yu-An, Meglioli, Mariano Cora, Dale, David, Dong, Ning, Duquenne, Paul-Ambroise, Elsahar, Hady, Gong, Hongyu, Heffernan, Kevin, Hoffman, John, Klaiber, Christopher, Li, Pengwei, Licht, Daniel, Maillard, Jean, Rakotoarison, Alice, Sadagopan, Kaushik Ram, Wenzek, Guillaume, Ye, Ethan, Akula, Bapi, Chen, Peng-Jen, Hachem, Naji El, Ellis, Brian, Gonzalez, Gabriel Mejia, Haaheim, Justin, Hansanti, Prangthip, Howes, Russ, Huang, Bernie, Hwang, Min-Jae, Inaguma, Hirofumi, Jain, Somya, Kalbassi, Elahe, Kallet, Amanda, Kulikov, Ilia, Lam, Janice, Li, Daniel, Ma, Xutai, Mavlyutov, Ruslan, Peloquin, Benjamin, Ramadan, Mohamed, Ramakrishnan, Abinesh, Sun, Anna, Tran, Kevin, Tran, Tuan, Tufanov, Igor, Vogeti, Vish, Wood, Carleigh, Yang, Yilin, Yu, Bokai, Andrews, Pierre, Balioglu, Can, Costa-jussà, Marta R., Celebi, Onur, Elbayad, Maha, Gao, Cynthia, Guzmán, Francisco, Kao, Justine, Lee, Ann, Mourachko, Alexandre, Pino, Juan, Popuri, Sravya, Ropers, Christophe, Saleem, Safiyyah, Schwenk, Holger, Tomasello, Paden, Wang, Changhan, Wang, Jeff, Wang, Skyler

Reviewed 2026-10-27. Explanation and interpretation by RLTasks. Benchmark ownership remains with its original authors.