Google 发布 Gemini 4 Hydrogen，智能水平接近 Claude Sonnet 5.5 而成本仅其三成
Google 六周内第三个新模型，54 分智能打平 Sonnet 5.5 和 GPT-6.1 Sol，幻觉率才 8%，是 Claude 的六分之一，跑长文档视觉推理很强。做文档分析和知识工作流的人可以重点看，但搞终端编程智能体的还是 Sonnet 更稳。
Google DeepMind 在六周内发布了第三款新模型 Gemini 4 Hydrogen，在 Artificial Analysis Intelligence Index 上以 xhigh 推理档拿到 54 分，距 Claude Sonnet 5.5 (max) 和 GPT-6.1 Sol (max) 各差 1 分，但每任务成本约为 Sonnet 5.5 的 32%，同时约为 GPT-6.1 Sol 的 2.5 倍。定价为每百万输入/输出 tokens $1.50/$7.50，1M 上下文窗口。
Hydrogen 首次为 Gemini 引入高于 high 的 xhigh 推理档，相比 high 可多拿 3 分智能，但输出 tokens 近乎翻倍，单任务成本从 $1.87 升至 $3.16。长文档视觉推理基准 GDP.pdf 上，medium 档以 33% all-pass 并列榜首；AA-Omniscience 上幻觉率低至 8%，远低于 Sonnet 5.5 (max) 的 43% 和 GPT-6.1 Sol (max) 的 52%。短板在终端智能体任务：Terminal-Bench 4.0 得 54%，低于 Sonnet 5.5 的 64%。输出速度约 200 tokens/秒，在 high/medium/low 档均处于时间-智能 Pareto 前沿。
Google's new Gemini 4 Hydrogen has Intelligence just below Claude Sonnet 5.5 and GPT-6.1 Sol, at a third of Sonnet’s cost but ~2.5x that of GPT-6.1 Sol
@GoogleDeepMind has released their third new model in six weeks. Gemini 4 Hydrogen introduces an xhigh reasoning level and scores 54 on the Artificial Analysis Intelligence Index, with strengths in visual reasoning and non-hallucination. This places it 1 point behind Claude Sonnet 5.5 (max) and GPT-6.1 Sol (max), at ~32% of Sonnet’s cost but ~2.5x that of GPT-6.1 Sol. With high reasoning, Gemini 4 Hydrogen matches the Intelligence of Gemini 4 Argon for ~19% of the Cost per Task
Key takeaways:
➤ The new xhigh reasoning level scores 54 on the Intelligence Index: xhigh is the first reasoning level above high on a Gemini model, and puts Hydrogen 1 point below Claude Sonnet 5.5 (max) and GPT-6.1 Sol (max), and 4 points ahead of Gemini 4 Argon (high). With default (high) reasoning, Gemini 4 Hydrogen scores 51, just behind GPT-6.1 Sol (xhigh, 52) and Claude Opus 5.5 (high, 52)
➤ Strong visual reasoning, presentation and non-hallucination: On GDP.pdf, a visual reasoning benchmark over long documents, it scores 33% all-pass on medium reasoning, the tied #1 score on the benchmark. On AA-Omniscience, Hydrogen has one of the lowest hallucination rates recorded at 8%, compared with 43% for Claude Sonnet 5.5 (max) and 52% for GPT-6.1 Sol (max). On AA-Briefcase, our agentic knowledge work evaluation, graders rate Hydrogen's presentation above other Gemini models, including Carbon
➤ Weaker on agentic terminal work: Hydrogen scores 54% on Terminal-Bench 4.0 and 50% on Terminal-Bench-Science 0.1, covering agentic coding and scientific research workflows in the terminal. Claude Sonnet 5.5 (max) scores 64% and 53%, and GPT-6.1 Sol (max) scores 56% and 58%. xhigh reasoning helps on the science tasks, lifting Terminal-Bench-Science from 41% at high to 50%, but makes no difference on Terminal-Bench 4.0 (54% at both). Science scores are even across domains, from 46% in earth sciences to 53% in physical sciences
➤ Low cost for its intelligence, with high token use at xhigh: Hydrogen is priced at $1.50/$7.50 per million input/output tokens. At xhigh it costs ~32% as much per task as Claude Sonnet 5.5 (max) for near-equal intelligence, but ~2.5x as much as GPT-6.1 Sol (max). xhigh nearly doubles output tokens compared with high for a 3 point gain in Intelligence, and Cost per Task falls from $3.16 at xhigh to $1.87 at high. Medium ($0.80) and low ($0.29) cost less again, but score 41 and 27 on the Intelligence Index
➤ On the Time per Task vs. Intelligence Pareto frontier: Gemini 4 Hydrogen has an output speed of ~200 output tokens per second. With high, medium, and low reasoning effort, Gemini 4 Hydrogen is on the Time per Task vs. Intelligence Pareto frontier, meaning no models are both more intelligent and have a lower Time per Task
Key model details:
➤ Context Window: 1M tokens
➤ Multimodality: Text, image, video, and speech input, with text output
➤ Reasoning efforts: Gemini 4 Hydrogen offers four reasoning levels (low, medium, high, and xhigh) with xhigh new in this release
➤ Pricing: $1.50/$7.50 per 1M input/output tokens. Cached input tokens receive a 95% discount ($0.075)
Congratulations to the @GoogleDeepMind team on the launch!
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. Key entities and technical topics under continuous tracking include Gemini 4 Hydrogen, Claude Sonnet 5.5, GPT-6.1 Sol, Google DeepMind.
Source attribution: curated from Artificial Analysis (@ArtificialAnlys). Cross-source corroboration: 4 independent sources have covered this development (including AI Will, Ate-a-Pi, rohanpaul_ai), confirming industry-wide signal strength.
