Hydrogen 提供四种思考级别：low（低）、medium（中）、high（高，默认值）以及新的 xhigh（超高）级别，而 Argon 仅提供 medium 和 high 两个级别。该模型的输入上下文窗口为一百万个 token，输出能力也为一百万个 token。其价格为每百万输入 token 1.50 美元，每百万输出 token 7.50 美元。缓存命中（cache hits）的价格为 0.075 美元。
在“xhigh”级别下，Gemini 4 Hydrogen 在 Artificial Analysis Intelligence Index 上得分为 54，紧随 Claude Sonnet 5.5 和 GPT-6.1 Sol 之后，后两者在其最大思考级别下均得分为 55。Gemini 4 Argon 的得分为 50。| 来源：Artificial Analysis
谷歌将 Hydrogen 定位为一款独立模型，并对 Gemini 3.8 Flash 进行了大幅升级。在默认思考级别下，谷歌表示其完成任务的速度提高了 2.5 倍。在 Terminal-Bench 4.1 上，分数从 18.2%（Flash）跃升至 57%（Hydrogen）。幻觉现象减少了五分之一，并且当工具调用失败或搜索结果为空时，模型的恢复能力更强，谷歌表示。
谷歌正在全球范围内向所有平台推出 Hydrogen。开发者可以通过 AI Studio 和 Android Studio 中的 Gemini API 访问该模型，付费的 Pro 和 Ultra 订阅用户则可以通过 Google Antigravity 使用它。企业客户通过 Gemini for Business 获得该模型，并且所有人都在 Gemini 应用和 Google 搜索中可以使用它。
在 Gemini 应用中，谷歌表示，在较长的对话中，该模型能更紧密地遵循语气、格式和指令，因此草稿、摘要和文档通常第一次尝试即可使用。Hydrogen 还可以从 Gmail 和 Drive 等谷歌应用以及 Airtable 和 Dropbox 等第三方应用中提取上下文。
谷歌声称 Hydrogen 也是搜索的一项“重大升级”。谷歌表示，该模型能更好地处理搜索查询，即使查询中包含拼写错误、多部分问题或非常具体的请求。搜索结果更具视觉吸引力且易于扫描，改进后的查询发散技术（query fan-out technique）能够引入更广泛的相关链接。
在谷歌的基准测试对比中，Gemini 4 Hydrogen 在所示的知识工作和多模态理解测试中击败了 Claude Sonnet 5.5 和 GPT-6.1 Terra。然而，Sonnet 在终端任务和计算机使用方面得分最高。| 来源：Google
在谷歌的编码工具 Antigravity 中，一个新的编排器（orchestrator）会在会话期间动态切换 Carbon 和 Hydrogen，而不是固守单一模型。在外部基准测试 Terminal-Bench 4.0 上，谷歌表示，该编排器的成功率几乎与 Carbon 相当，同时资源使用量减少了 24%，处理时间缩短了 19%。
根据 Artificial Analysis 的数据，在 AA-Omniscience 基准测试中，Hydrogen 的胡编乱造率仅为 8%。在评估智能体知识工作的 AA-Briefcase 中，它在呈现质量方面也优于其他 Gemini 模型，包括 Carbon。
Hydrogen 在智能体终端工作方面较弱，在 Terminal-Bench 4.0 上得分为 54%，在 Terminal-Bench-Science 0.1 上仅得分为 50%。Claude Sonnet 5.5（max）在这两项测试中分别达到 64% 和 53%，而 GPT-6.1 Sol（max）的得分分别为 56% 和 58%。
在性价比方面，Artificial Analysis 指出，Hydrogen 在 xhigh 级别下的每次任务成本约为 3.16 美元，大致相当于 Claude Sonnet 5.5（max）在几乎相同智能水平下的成本的三分之一，但大约是 GPT-6.1 Sol（max）成本的 2.5 倍。
“xhigh”思考级别将 Gemini 4 Hydrogen 的分数从 51 提升至 54，但需要比“high”级别多近一倍的输出 token。每次任务的平均成本从 1.87 美元上升至 3.16 美元。| 来源：Artificial Analysis
在“high”级别下，成本降至 1.87 美元，“medium”（中）级别为 0.80 美元，“low”（低）级别为 0.29 美元。不过，在较低级别下，智能分数急剧下降，其中“medium”级别仅达到 41 分，“low”级别仅为 27 分。Artificial Analysis 指出，xhigh 级别的输出 token 数量几乎是 high 级别的两倍，这解释了价格的跳跃。在 high、medium 和 low 层级，该模型位于帕累托前沿（Pareto frontier），意味着没有其他模型在这些价格点上既更便宜又更聪明。
查看原文
Google has released Gemini 4 Hydrogen, a fast general-purpose AI model meant for developers and everyday users.
Unlike the frontier models Gemini 4 Carbon and Gemini 4 Argon, which Google designed for deep, long-horizon reasoning on hard problems, Hydrogen is meant to handle everyday tasks quickly and cheaply. It appears to be the counterpart to the earlier Flash series.
That comparison may sell it short, though. According to Google, Hydrogen beats the larger Argon on the Artificial Analysis Intelligence Index at the default "high" thinking level (51 vs. 50) and reaches up to 54 at the highest level, "xhigh."
Hydrogen offers four thinking levels: low, medium, high (the default), and a new xhigh tier, while Argon offers only medium and high. The model has a one-million-token context window for input and can output one million tokens. It costs $1.50 per million input tokens and $7.50 per million output tokens. Cache hits cost $0.075.
At "xhigh," Gemini 4 Hydrogen scores 54 on the Artificial Analysis Intelligence Index, just behind Claude Sonnet 5.5 and GPT-6.1 Sol, which each score 55 at their maximum thinking level. Gemini 4 Argon trails at 50. | Source: Artificial Analysis
Hydrogen apparently ends up both more capable and cheaper than Argon. Adding to the confusion, when Google announced its new frontier model Carbon just two days ago, the company recommended sticking with Argon for daily coding work. Hydrogen should make that advice moot, leaving Argon obsolete less than four weeks after its release.
Hydrogen delivers a major jump over the previous Flash generation
Google pitches Hydrogen as a standalone model and a big upgrade over Gemini 3.8 Flash. At the default thinking level, Google says it finishes tasks 2.5 times faster. On Terminal-Bench 4.1, the score jumps from 18.2 percent (Flash) to 57 percent (Hydrogen). Hallucinations dropped by a factor of five, and the model recovers better when a tool call fails or a search comes up empty, Google says.
On open-ended agent tasks like research, data analysis, and code navigation, Hydrogen ranks fifth on the Agent Arena leaderboard. Google says it takes first place on the Vals Tax Agent Bench with 52.3 percent and ties for first on the Vals Legal Research Bench with 55.8 percent.
Category
Benchmark
Gemini 4 Hydrogen
Gemini 4 Carbon
Gemini 4 Argon
General Abilities
AA Index v5.0
54 (xhigh, 5.1)
59
50
Vals Index v2.2
—
70.4%
69.2%
Agentic coding
SWE-sweep
13.5%
9.6%
4.3%
FrontierSWE 2
—
61.2%
55.0%
Terminal-Bench 4.1 (cheating-adjusted)
57.0%
—
—
Terminal Bench 4.0 (AA)
—
65.2%
57.1%
Knowledge Work
Agents’ Last Exam v1.1
71.6%
77.4%
69.0%
AutomationBench
76.1%
—
—
AutomationBench (Zapier)
—
53.9%
51.3%
Vending-Bench 2 (Account Balance, U.S. Dollars)
$14,549
$16,484
$13,718
Computer Use
OSWorld-2.1 (offline subset)
77.6%
81.5%
74.7%
Multimodal Understanding
MKA (Climb WSR accuracy)
53.4%
—
—
Chartography
66.6%
72.5%
71.6%
Blueprint Bench 2 (Similarity Score)
—
58.6%
54.4%
Long Context
GraphWalks (256k to 1M, BFS)
—
96.2%
84.2%
Science and Mathematics
Terminal-Bench-Science 0.1
51.4%
—
—
RiemannBench
—
80.0%
76.0%
Terminal-Bench-Science 0.1 (AA)
—
64.8%
52.9%
Reasoning
HLE-Diamond
58.8%
—
—
Cybersecurity
CWE-bench
—
71.0%
68.0%
ExploitGym
—
54.8%
42.0%
SEC-bench Pro
—
88.2%
83.4%
For multimodal knowledge work like summarizing large PDFs, spreadsheets, or videos, Hydrogen supports up to one million output tokens on top of its one-million-token input window. It scores 53.4 percent on Google's new Multimodal Knowledge Agent Benchmark and 71.6 percent on Agents' Last Exam v1.1.
Hydrogen is available now
Google is rolling Hydrogen out globally across all platforms. Developers get access through the Gemini API in AI Studio and Android Studio, while paying Pro and Ultra subscribers can use it through Google Antigravity. Business customers get it through Gemini for Business, and it's available to everyone in the Gemini app and Google Search.
In the Gemini app, Google says the model sticks more closely to tone, format, and instructions over longer conversations, so drafts, summaries, and documents are more often usable on the first try. Hydrogen can also pull in context from Google apps like Gmail and Drive, as well as third-party apps like Airtable and Dropbox.
Google claims Hydrogen is a "significant upgrade" for Search, too. The model handles search queries better, even when they contain typos, multi-part questions, or very specific requests, Google says. Results are more visual and easier to scan, and an improved query fan-out technique pulls in a wider range of relevant links.
In Google's benchmark comparison, Gemini 4 Hydrogen beats Claude Sonnet 5.5 and GPT-6.1 Terra on the knowledge work and multimodal understanding tests shown. Sonnet, however, scores highest on terminal tasks and computer use. | Source: Googl
In Antigravity, Google's coding tool, a new orchestrator switches dynamically between Carbon and Hydrogen within a session instead of sticking with one model. On the external benchmark Terminal-Bench 4.0, Google says the orchestrator nearly matches Carbon's success rates while using 24 percent fewer resources and cutting processing time by 19 percent.
Independent test finds Hydrogen rarely hallucinates but lags on terminal work
An independent evaluation by Artificial Analysis puts Hydrogen roughly on par with Claude Sonnet 5.5 at its highest thinking level. At the default "high" level, the score drops to 51, slightly behind GPT-6.1 Sol (xhigh, 52) and Claude Opus 5.5 (high, 52).
On the AA-Omniscience benchmark, Hydrogen makes things up only 8 percent of the time, according to Artificial Analysis. It also beats other Gemini models, including Carbon, on presentation quality in AA-Briefcase, which evaluates agentic knowledge work.
Hydrogen is weaker at agentic terminal work, scoring 54 percent on Terminal-Bench 4.0 and just 50 percent on Terminal-Bench-Science 0.1. Claude Sonnet 5.5 (max) reaches 64 and 53 percent respectively, while GPT-6.1 Sol (max) scores 56 and 58 percent.
On price-performance, Artificial Analysis puts Hydrogen at about $3.16 per task at xhigh, roughly a third of what Claude Sonnet 5.5 (max) costs at nearly the same intelligence level but about 2.5 times as much as GPT-6.1 Sol (max).
The "xhigh" thinking level lifts Gemini 4 Hydrogen from 51 to 54 points but needs nearly twice as many output tokens as "high." Average cost per task rises from $1.87 to $3.16. | Source: Artificial Analysi
At "high," costs drop to $1.87, at "medium" to $0.80, and at "low" to $0.29. Intelligence scores fall sharply at the lower levels, though, with medium reaching only 41 and low just 27 on the index. Artificial Analysis notes that xhigh uses nearly twice as many output tokens as high, which accounts for the price jump. At the high, medium, and low tiers, the model sits on the Pareto frontier, meaning no other model is both cheaper and smarter at those price points.
AI News Without the Hype – Curated by Humans
Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.
Subscribe now
Studio