Gemini 4 Hydrogen 成为 Agent Arena 速度最快的模型
做 Agent 应用的可以看看这份实测数据：Gemini 4 Hydrogen 单步只要 7.3 秒，10 分钟完成 82% 任务，速度比 Claude Sonnet 5.5 和 GPT-6.1 Sol 快不少，质量分数还没掉。对任务等待时间敏感的团队值得对比一下。
GoogleDeepMind 的 Gemini 4 Hydrogen 在 Agent Arena 排行榜前十中速度第一。一个典型 Hydrogen 步骤耗时 7.3 秒，比 Claude Sonnet 5.5 快 2.7 倍，比 GPT-6.1 Sol 快 3.1 倍。
按会话时长统计，82% 的 Hydrogen 任务在 10 分钟内完成，GPT-6.1 Sol 为 55%，Claude Sonnet 5.5 为 44%；30 分钟内完成率 Hydrogen 达 97%，Sol 和 Sonnet 5.5 分别为 81% 和 78%。同时其净改进分数与两个对手持平，速度优势没有以质量为代价。
测量口径为 Agent Mode 任务中的一次模型 API 调用，计时从首个模型请求到最后一个流式回复结束，不含工具执行时间。
Gemini 4 Hydrogen by @GoogleDeepMind is the fastest model in the Agent Arena top 10. A typical Hydrogen step takes 7.3 seconds, about 2.7x faster than Claude Sonnet 5.5 and 3.1x faster than GPT-6.1 Sol. Faster steps mean less time waiting on tasks. Across Agent Arena sessions, Hydrogen spends under 10 minutes on 82% of its tasks, compared with 55% for GPT-6.1 Sol and 44% for Claude Sonnet 5.5. Within 30 minutes, that rises to 97%, versus 81% for Sol and 78% for Sonnet 5.5. And it isn't a quality trade-off: Hydrogen's net improvement is on par with both models. How we measure it: A step is one model API call in an Agent Mode task. All times run from the first model request to the last streamed reply, without tool execution.
This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to US-China foundation model benchmarks and commercialization comparison and AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Gemini 4 Hydrogen, Claude Sonnet 5.5, GPT-6.1 Sol, GoogleDeepMind.
Source attribution: curated from lmarena.ai (@lmarena_ai). Cross-source corroboration: 9 independent sources have covered this development (including Artificial Analysis, Philipp Schmid, Demis Hassabis), confirming industry-wide signal strength.
