Gemma 4：同等參數規模下最強大的開源模型，專為進階推理與 Agent 工作流打造
Original: Gemma 4: Byte for byte, the most capable open models
Google DeepMind has today officially released its latest generation of open-source model series — Gemma 4. The company positions it as "the…
Google DeepMind 正式發表全新開源模型 Gemma 4。官方宣稱其為「同等參數規模下最強大的開源模型」，在智慧表現上達到新高度。該系列模型特別針對進階推理與自主 Agent 工作流進行優化，為開發者提供更高效、更具性價比的開源 AI 選擇。
Google DeepMind has today officially released its latest generation of open-source model series — Gemma 4. The company positions it as "the smartest and most capable open-source model to date, byte for byte." This means that at equivalent parameter scale and computational resource consumption, Gemma 4 delivers performance that surpasses competing models in the same class.
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on Google DeepMind Blog →Summaries are AI-generated; the original article is authoritative.