| 1M 代币(原为 64K) |
| 介绍价 | 每 100 万个输入代币 2 美元,每 100 万个输出代币 10 美元 |
|---|
| 缓存输入价格 | 输入代币价格 95% 折扣 |
|---|
| 深SWE v1.1 | 77.9%(谷歌:最新技术) |
|---|
| AutomationBench (扎皮尔) | 51.3%,排名第一 |
|---|
| LVBench(长视频) | 91.7%,最先进的 |
|---|
| CWE 工作台 v1 | 68%,并列第一 |
|---|
所有数据均来自谷歌自己在公告中的说法;该页面没有在文本中给出竞争对手的分数,因此不会保存比较图。 · 来源
Estimate from the version's published specs, benchmarks and reviews, 0-5; scores are only comparable within one criteria year. Maker's 30 Sep 2026 post: 1M output-token limit (up from 64K), DeepSWE v1.1 77.9% (Google-run harness), LVBench 91.7%, CWE-bench v1 68.0% tied first; $2/$10 per M tokens intro then $4/$20. eesel (citing Artificial Analysis) gives Intelligence Index 53 vs Opus 5.5 at 58, Terminal-Bench 4.0 57.1% (4th), cost $1.99 promo / $3.98 per task, 62K output tokens per task. Speed not published (AA lists N/A); not API-callable at review time. Input context window not stated on the opened page, so context reflects the 1M output limit and GraphWalks 84.2% at 256K-1M. Only two independent write-ups opened; no hands-on tests found.[1]
Gemini 4 Argon is the best model Google has shipped, and on paper it lands in the same tier as GPT-6 Astra.
Independent evaluations indicate that while Argon scores competitively on several key intelligence benchmarks, it shares the lead rather than achieving a clear, universal advantage.
| Gemini 4 Argon review: a great model you can't use yet · 2026年10月1日 | 0.70 |
|---|---|
| Google Gemini 4 Argon closes the gap with OpenAI and Anthropic, but doesn’t take a clear lead · 2026年10月1日 | 0.20 |
读者上传的照片,与图钉带来源的媒体分开显示。你可以为吃到或看到的内容评分,在餐厅图钉上还能直接在照片上标记菜品。
第一项始终是图钉的来源。总体可信度是各份资料对上方所用开始和结束时间支持程度的加权平均;资料每比最新的一份旧 180 天,权重减半。
Google 于 9 月 30 日宣布向值得信赖的网络防御者推出 Gemini 4 Argon。广泛的付费用户发布于 10 月 13 日发布,并由 15308 号引脚覆盖,该引脚具有规范的发布标题。Pin 4810 是公告副本,而不是发布标题。
DeepMind's Gemini page now leads with Gemini 4 Argon and carries its benchmark table against GPT-6 Astra, Claude Fable 5.1 and Claude Opus 5.5, plus the four safeguard areas Google is strengthening before broad availability.
有遗漏或错误吗?用你自己的话说明:能佐证此图钉的链接、不同的开始或结束日期及理由,或缺失、有误的信息。AI 会对照此图钉的来源进行核实,搜索更好的来源,并添加任何支持你说法的页面。图钉自身的来源仍然最重要。AI 也会查看图片:显示的是别的东西或显示效果差的图片会被移到后面或替换。
原标题: Gemini 4 Argon Announced
| 基准测试 | Gemini 4 Argon | GPT-6 Astra | Claude Fable 5.1 | Claude Opus 5.5 |
|---|---|---|---|---|
| Vals Index(知识工作) | 68.9% | 63.1% | 65.8% | 67.0% |
| AutomationBench(知识工作,得分) | 51.3% | 41.4% | 31.4% | 42.5% |
| Vals Finance Agent v2(知识工作) | 65.4% | 53.5% | 58.9% | 58.6% |
| Harvey's Legal Agent Benchmark(知识工作) | 19.6% | 5.4% | 6.7% | 3.8% |
| DeepSWE v1.1(智能体编程) | 77.9% | 74.1% | 67.4% | 74.2% |
| FrontierSWE v2(智能体编程) | 55.0% | 65.5% | 56.3% | 62.3% |
| Vibe Code Bench(智能体编程) | 91.9% | 89.6% | 90.3% | 90.3% |
| Terminal-bench 4.0(智能体编程) | 57.4% | 58.2% | 57.9% | 66.4% |
| PostTrainBench(机器学习工程) | 45.3% | 44.3% | 40.2% | 49.3% |
| Terminal-Bench Science 0.1(科学与数学) | 57.6% | 68.1% | 52.6% | 63.3% |
| LABBench 2(科学与数学) | 88.8% | 85.4% | 68.6% | 73.1% |
| RiemannBench(科学与数学) | 76.0% | 72.0% | 65.6% | 69.6% |
| GraphWalks(长上下文,最高128k,BFS (F1)) | 99.7% | 98.7% | 91.4% | 90.6% |
| GraphWalks(长上下文,256k至1M,BFS (F1)) | 84.2% | 71.8% | 65.0% | 66.8% |
| Agent's Last Exam(计算机操作,通过率) | 39.5% | 34.2% | — | 38.2% |
| OSWorld-2.0(计算机操作,离线子集部分得分) | 69.2% | 72.6% | — | — |
| Chartography(多模态理解) | 71.6% | 71.0% | 46.2% | 66.3% |
| LVBench(多模态理解) | 91.7% | 87.5% | 79.7% | 83.7% |
| CWE-bench v1(网络安全) | 68.0% | 68.0% | 58.0% | 67.0% |
同一事件,另外被标记了 1 次。 在时间线上它们会叠放,关注最多(其次浏览最多)的在最上面:就是这个。