Abstract
For scientific progress, we need benchmarks that test the limits of state-of-the-art models, and evaluation methods that inform us about failure cases. As models get stronger, standard benchmarks for machine translation are approaching saturation. Further, automatic translation metrics are unreliable, vulnerable to reward-hacking, and provide unactionable assessments. Even gold human evaluation is not problem-free, because it often lacks reproducibility, objectivity, and scalability. Overall, this prevents us from tracking objective progress in the field and identifying pathways for improvement. We introduce the Last Translation Benchmark, a collection of human-authored and peer-reviewed examples (texts, images, audio, videos) that break leading machine translation models. We also present a new evaluation approach: each example comes with handcrafted verification rules describing concrete failure cases on that example, therefore allowing reliable and actionable future evaluation. The Last Translation Benchmark is a live dataset that accepts ongoing contributions. The latest version is LTBv1, containing accepted contributions prior to September 1st 2026, with future releases planned as new data is continuously collected.
BibTeX
@article{zouhar2026last,
title={Last Translation Benchmark},
author={Zouhar, Vil{\'e}m and Bafna, Niyati and Choudhary, Mukund and Z{\"u}fle, Maike and Rajaee, Sara and Chen, Pinzhen and Vamvas, Jannis and Papi, Sara and de Gibert, Ona and Malik, Bhavitvya and others},
journal={arXiv preprint arXiv:2609.04173},
year={2026}
}
