North Small Translate hits 83.6 on WMT, outperforming DeepL and Google Translate
cohere · x · 2026-09-11
Cohere shared benchmark details for North Small Translate: an 83.6 average score on the WMT benchmark across all languages, beating DeepL, Google Translate, and open alternatives including GLM 5.2 and Mistral Large 3.
Related event: Cohere's Translate Model Beats DeepL and Google on WMT Benchmark(4 posts)→
More from Models
- OpenAI confirms progress on second Millennium Prize problem, sparking RSI debate — AndyMasley · 2026-09-11
- humans& launches Persimmon, a large-scale model built to realistically simulate how people interact — Scobleizer · 2026-09-11
- DeepSeek releases V4.1-Flash: 552B MoE claimed to beat V4-Pro on cost and speed — eyishazyer · 2026-09-11
- Arch breakdown: dropping convs for Muon optimizer, 3x3 pixel unshuffle for vision — stochasticchasm · 2026-09-11
- FrontierMath Tier 4 fully solved 14 months after launch; LEAP panel forecasts lag reality — Afinetheorem · 2026-09-11
- One Pokédex, four model setups: hands-on comparison of GPT-6 Astra and DeepSeek V4.1 Flash — kevinkern · 2026-09-11