Sakana AI's Namazu translation model claims to beat Google Translate and DeepL
SakanaAILabs · x · 2026-08-22
Sakana AI upgraded its translation service Sakana Translate to the new-generation Sakana Namazu model, maintaining bidirectional Japanese-English-Chinese translation while improving output naturalness.
On its own 160-task Japanese-English benchmark, Sakana claims its output was judged better than all comparison targets — including Google Translate and DeepL — in over 50% of cases. Note this is a vendor-run evaluation, not an independent benchmark.
Related event: Sakana AI Upgrades Sakana Translate with New Namazu Model(5 posts)→
More from Models
- ChatGPT Pro 'Unlimited' Image Generation Actually Rate-Limited — DaBobcat · 2026-08-24
- Speculation: Ox Alpha Allegedly a Multi-Party Collaboration — teortaxesTex · 2026-08-24
- Carnice-V3-27b: Beats 10x Larger Models Locally — TheMoonMidas · 2026-08-24
- Grok ports DOOM to ESP32-S chip at high frame rate — yunta_tsai · 2026-08-24
- Open source models aren't just about cost; training can push the Pareto frontier — ypatil125 · 2026-08-24
- Critique on Quantization Benchmarks: When Quant Beats Reference, It's Overfitting — teortaxesTex · 2026-08-24