Last Translation Benchmark Is Live: Contribute 10 Examples, Get Co-authorship
zouharvi · x · 2026-09-04
Last Translation Benchmark is a live paper+dataset still open for contributions. It tackles saturated benchmarks and unreliable metrics by collecting inputs (text, image, audio, video) that provably break state-of-the-art translation models, each with an automatic pass/fail verification rule. Contributors with 10 approved submissions earn co-authorship on the live publication. LTBv1 already has 3456 examples (90MB) on arXiv and a Hugging Face leaderboard, with rolling future releases.
Related event: The Last Translation Benchmark Targets Translation Model Weak Spots(2 posts)→
More from Research
- ACS Research Launches Free Platform Giving Researchers Access to Llama 3.1 Base Models — jankulveit · 2026-10-21
- LessWrong Essay Introduces LM Psychology: Just Talking to an AI Still Beats Fancy Evals — jankulveit · 2026-10-21
- Stanford researcher clashes over genomics foundation model's cherry-picked variant prediction benchmarks — anshulkundaje · 2026-10-21
- Gemini Agents Crack 59-Year-Old Fusion Math Conjecture in Hours — DynamicWebPaige · 2026-10-21
- Bombadil: a foundation model that decodes plants' bio-electrical signals — tdhopper · 2026-10-21
- TrackEverything: CMU and Meta open-source a 3D tracker for all points in 1000+ frame videos — AdamWHarley · 2026-10-21