Last Translation Benchmark adds North, Mistral Large 4, Qwen 3.8; open for coauthorship
zouharvi · x · 2026-10-08
The Last Translation Benchmark (LTB) is still accepting submissions — 10 accepted entries in any language earns coauthorship. The leaderboard now includes the latest models such as Cohere's North Small Translate, Mistral Large 4, and Alibaba's Qwen 3.8, with an open invitation for teams to add their models and try to beat the benchmark.
Related event: Last Translation Benchmark opens submissions, adds new models(2 posts)→
More from Research
- Performance estimation: SDPs were auto-proving algorithm convergence long before LLMs — burny_tech · 2026-10-08
- ThunderSyncRL: Sync agentic RL gets up to 1.9x faster by overlapping gradients with rollouts — YouJiacheng · 2026-10-08
- AI-designed drugs reach late-stage trials as Insilico's rentosertib recruits Phase 3 — nathanbenaich · 2026-10-08
- EngramEdit: decoupled factual knowledge edits in LLMs via conditional memory — ModalityDance · 2026-10-08
- Researcher says he used Claude Code to find a previously unknown planet — pyduan · 2026-10-08
- Chrome's new DecisionModel API reverse-engineered: prompts, limits and engine tests — dejanseo · 2026-10-08