奥特曼「红色警戒」5个月后,GPT Image 2屠榜,断层领先反杀谷歌

marsbitPublished on 2026-04-27Last updated on 2026-04-27

【导读】被Google按了半年头,OpenAI终于祭出一记反杀。GPT Image 2上线12小时,就登顶Arena文生图榜,领先Nano Banana 2达241分。Arena官方称,这是Image Arena文生图排行榜迄今最大的分差。

发布当天,三榜通杀。

GPT Image 2上线12小时,Text-to-Image(文生图)、Single-Image Edit(单图编辑)、Multi-Image Edit(多图编辑)三个分榜全部登顶。

Arena官方原话:「a clean sweep」(全胜)。

文生图主榜,GPT Image 2 1512分,Nano Banana 2 1271分。241分差距,Arena史上最大。

「没有任何模型曾以这种差距统治过Image Arena」,Arena官方表示。

在Image Arena所有盲测对决中,GPT Image 2的胜率是93%:100张图配对盲选,93张人们选了OpenAI那张。

「如果把DALL-E看作洞穴壁画,把Images 1.0视为古代艺术,那么Images 2.0就是文艺复兴」。

OpenAI在发布会开场中这样介绍Images 2.0,奥特曼更是将它称作跨代升级:

这好像一下子从GPT-3跃升到了GPT-5。

https://www.youtube.com/watch?v=sWkGomJ3TLI

OpenAI官方API文档对Images 2.0给出了一个最高级的评价。

https://developers.openai.com/api/docs/models/gpt-image-2

但真正的故事,并不在数据里。

被Google压了半年,OpenAI总算扳回一局

时间倒回2025年8月。

Google放出了Nano Banana。这个在Gemini里嵌入的图像生成模型,在C端瞬间引爆。

三个月后的Q3财报会上,Google CEO Sundar Pichai亲口披露了一组数字:Gemini月活,从7月的4.5亿涨到10月的6.5亿。

Google Labs负责人Josh Woodward称,这一增长很大程度上来自Nano Banana带动的图像生成热潮。

11月,Google再发Nano Banana Pro。文本渲染能力惊艳,AI图像第一次能把字写对,OpenAI在C端被反超。

11月18日,Google再补一刀。Gemini 3发布即登顶LM Arena,1501分,首个突破1500的前沿模型。

这一月底,奥特曼对全公司发了一份「红色警戒」(code red)的内部备忘录。

据The Information报道,奥特曼私下告诉员工,Gemini 3可能给OpenAI带来经济逆风。Yahoo Finance后续披露:code red之下,OpenAI暂停了AI Agent等其他产品的研发,资源全部倾斜到ChatGPT。

12月,OpenAI仓促拿出GPT Image 1.5。Arena第一,但C端没能引爆。

2026年2月,Google再补一刀,Nano Banana 2登场,Arena再度领先。

OpenAI又输了一次。

一直到4月21日,GPT Image 2上线,OpenAI这才实现反超,重新扳回一局。

画图AI将被重新定义

GPT Image 2凭什么能领先241分?

核心答案藏在架构层面。

GPT Image 2不是Stable Diffusion那一代的扩散模型。

OpenAI研究负责人Boyuan Chen称这是「revamped from scratch」(从零重构)的「generalist model」(通用模型),OpenAI的内部叫法是「图像版的GPT」。

但Chen在press briefing时拒绝公开承认它具体是扩散还是自回归架构。

外界普遍把它理解为「带推理规划的图像生成系统」:画之前先规划,再下笔。这正是GPT Image 2和上一代图像模型最大的不同。

OpenAI在官方说明里给了它一个新标签:首个具备原生思考能力的图像模型(image model with native thinking capabilities)。

画之前先想、画完自己检查、需要时联网搜索资料、一次能产出8张前后连贯的图。

这不是画笔,是会思考的视觉助理。

Arena榜单分项数据显示:

文字渲染(Text Rendering)单项,GPT Image 2比前代涨了316分;卡通动漫和人像各涨296分;3个产品/3D/写实分类,整体在+247到+277分区间。

文字渲染是2025年11月Nano Banana Pro首次解决的问题,但当时准确率94%。GPT Image 2把它推到了99%。

OpenAI发布会现场演示:让GPT Image 2画一碗米饭,其中只有一粒米上写有模型名字。

具体到能力展示,OpenAI总裁Greg Brockman在自己的X账号上做了示范。

第一个案例,老照片修复。

褪色发黄的家庭老照片,一个提示词,立刻变身高清彩色版。

OpenAI官方API文档里那句「high-fidelity image inputs」(高保真图像输入),说的就是模型对原图细节的保留能力:输入端能精确读取褪色的、破损的、模糊的老照片细节,输出端才能重新渲染出清晰版。

第二个案例中,Brockman转发了用户@doodlestein的一组测试图:用同一个复杂提示词让GPT Image 2画一张数学解释图。

他评价说,即便是复杂提示词,GPT Image 2也能生成风格各异的图。

@doodlestein 测试GPT Image 2用同一个提示词画一张线性代数解释图。模型一口气画出4个完全不同的版本:同样是Mona Lisa+特征向量教学,每个版本的构图、配色、信息密度完全不同。

这个案例真正价值不在「能画数学图」,而是解决了过去两年中AI生图的一个重要的痛点:输出单一、变体可控性差。

GPT Image 2第一次让「一个prompt给我4个完全不同的方向」变成了产品级能力。

业内一位LM Arena资深测试者点评道:

GPT Image 2和Nano Banana Pro之间的差距,跟Nano Banana Pro和DALL-E之间的差距一样大。

跨了整整一代。

GPT Image 2 Thinking模式生成的manga风格漫画页:从一个简单提示词出发,模型保持角色一致性、铺出多格剧情。

DALL-E退役,Adobe Canva被逼到墙角

发布当天,下游工具集成的速度比技术圈预期的还快。

Figma、Canva、Adobe Firefly、fal、Hermes Agent,全部在4月21日当天完成集成。

API定价更是暗藏杀机:

高质量出图$0.21一张;ChatGPT Plus $20一个月,图像生成已经包含在套餐里。

这个差价背后,可能带来2026年图像生成行业最大的产业重构。

GPT Image 2生成的photorealistic candid(写实抓拍)。海岸、阴天、复古车、胶片质感——这种过去要专业摄影师外拍+后期才能达到的视觉效果,现在API $0.21一张。OpenAI研究员Gabriel Goh说,photorealism是他对这个模型最兴奋的能力。

5月12日,DALL-E 2和DALL-E 3正式退役。

它们是2022年开启了整个AIGC视觉革命的开山祖师。三年后,被OpenAI自家的继承者,亲手送入历史。

OpenAI在官方发布说明里提到:

图像不是装饰,是语言。一张好图做的事和一个好句子一样:选择、排列、揭示。

这代表了一种产品哲学的转向。

当然,也不是没有反方声音。ZDNet在实测中发现,GPT Image 2无法准确复刻品牌logo,连ZDNet自己的logo都被画歪了。

Nano Banana 2在portrait realism和multi-reference一致性上仍有优势。

GPT Image 2虽然还不够完美,但赛道格局已经出现了变化。

渲染时代结束了,推理时代刚开始

Google把推理塞进图像模型里。OpenAI把图像工具塞进推理模型里。242分Elo差距测的就是二者架构上的差异。

implicator.ai的这句评价,划分了图像生成的两个时代。

2022到2025年,是渲染时代。

DALL-E、Midjourney、Stable Diffusion,目标都是「画得像」。模型是画笔,用户是画师,prompt是画稿。

GPT Image 2代表的是一个推理时代。

模型先思考再下笔,能搜索、能自检、能完成任务。它不是画笔,是会画画的助手。

GPT Image 2发布真正值得重视的,是图像生成走向「会思考」这件事本身。

短期看,Black Forest Labs(Flux 2)麻烦可能最大。

Kingy AI直言:作为diffusion-first(扩散为先)的厂商,Flux 2的整条技术流水线在架构上和「token-by-token」的推理路线是冲突的。

要么融合,要么重写,没有第三条路。

中期看,Google可能会在下个季度反击。Nano Banana 3,或者Imagen-Reason,时间不会太久。

长期看,这件事的影响远不止图像生成。

当AI开始用「思考」来产出图像、视频、音频、代码,整个生成式AI的范式都会跟着发生变化。

去年12月,奥特曼在备忘录里敲下「code red」的时候,应该没想到五个月后会以这种方式回到Arena榜首。

但这次反杀的真正意义,可能不是OpenAI赢了Google,而是OpenAI改写了图像生成赛道的规则。

Arena.AI单图编辑榜(Image Edit Arena):GPT Image 2 (medium) 仍以1510+分继续登顶,第二、三、四、五名全部被OpenAI自家模型和Google Gemini系列占据。https://arena.ai/leaderboard/image-edit

Google下一拳什么时候出?这个问题决定了2026下半年AI格局的走向。

而在那一拳挥出来之前,GPT Image 2会在Arena榜首坐多久,没人知道。

参考资料:

https://x.com/gdb/status/2048449695622586576

https://arena.ai/leaderboard/image-edit

本文来自微信公众号“新智元”,编辑:元宇

Trending Cryptos

Related Reads

GPT-5.6 Countdown: Abandon the Illusion of a Single API, Computational Iteration Can't Outpace a Single Page of Compliance

In mid-June, three seemingly independent industry events—the compliance-driven throttling of Fable 5, the open-sourcing of GLM-5.2, and the leaked release timeline for GPT-5.6—are pushing the global AI industry toward a watershed moment. These shifts signal a fundamental restructuring of the industry's underlying logic. First, **"usability" has substantially overtaken "advanced capabilities"** as the primary weight, pushing the global large language model (LLM) supply chain into a "dual-track" phase of controlled closed-source and local open-source coexistence. Second, **the competitive moats of closed-source giants are shifting**. Their technical focus is moving from "language intelligence" toward "spatial intelligence (world models)"—a domain heavily reliant on computing power. Third, faced with常态化 transnational compliance risks, **a "model-agnostic" decoupled design has become a survival necessity for application-layer developers to maintain business continuity.** The article details how Anthropic's Fable 5, despite its advanced engineering feats, was restricted for non-U.S. citizens within 72 hours of launch, highlighting how geopolitical compliance can instantly limit even the most advanced models. In response, the open-source camp, exemplified by Zhipu AI's MIT-licensed GLM-5.2, is gaining market share by offering stable performance improvements and significant cost advantages (up to 70% savings for enterprises), while achieving full adaptation with domestic semiconductor platforms. Meanwhile, closed-source leaders like OpenAI are pivoting. The anticipated GPT-5.6 reportedly shifts focus from language to spatial intelligence and world models, aiming to rebuild a generational gap in areas like 3D understanding, simulation, and industrial design that demand immense compute. The core conclusion is that the LLM supply chain's logic has changed. Enterprises must now evaluate infrastructure based on a composite of technical performance and policy compliance. For developers, complete reliance on a single closed-source API poses unacceptable risk. Implementing a truly model-agnostic architecture—enabling swift switches to compliant, locally deployable open-source alternatives—is no longer just good practice but a fundamental baseline for business continuity.

marsbit1h ago

GPT-5.6 Countdown: Abandon the Illusion of a Single API, Computational Iteration Can't Outpace a Single Page of Compliance

marsbit1h ago

Is the 'Token Subsidy War' Among AI Giants Almost Over?

The article discusses the ongoing "token subsidy war" among AI giants like OpenAI and Anthropic, questioning whether it's nearing its end. It reveals that current AI subscription prices are heavily subsidized, with some plans offering tokens at up to 70 times the actual cost to attract and retain heavy users, especially developers and enterprises. This strategy mirrors past internet-era subsidy battles, but with a key difference: AI tokens lack "lock-in" effects. Unlike ride-hailing or food delivery apps, users can easily switch between AI providers as APIs become standardized, making it difficult for companies to raise prices post-subsidy. The piece highlights a structural asymmetry in the competition. Giants like Google, with massive advertising revenue, can afford to subsidize tokens indefinitely, akin to using "tokens as a weapon." In contrast, venture-backed companies like OpenAI and Anthropic face pressure to become profitable, especially as they approach IPO. The article cites Google Ventures founder Bill Maris, who suggests Google could slash token prices by 80%, putting immense pressure on competitors. Two potential endgames are presented: the "internet service" model (subsidize, monopolize, then raise prices) and the "utility" model (tokens become a standardized, low-margin commodity like electricity). Given the low switching costs, the latter seems more likely. The competition may not have a single winner but could instead accelerate AI's evolution into a foundational, infrastructure-level technology, akin to a public utility. For now, users continue to benefit from heavily subsidized token costs.

marsbit1h ago

Is the 'Token Subsidy War' Among AI Giants Almost Over?

marsbit1h ago

Beyond the Stadium: The Profitable Games Surrounding the World Cup

"Beyond the Pitch: The Profit Game Around the World Cup" The FIFA World Cup transcends being a sporting spectacle, evolving into a massive global arena for speculation and profit-seeking. The 2026 tournament has amplified this dynamic, creating a multi-layered ecosystem of financial opportunism alongside the football. **Prediction markets** have surged into the mainstream. Platforms like Polymarket and Kalshi saw trading volumes for World Cup contracts soar, attracting new users with their financial trading model and high-profile, chain-based wealth stories that overshadow traditional sports betting in terms of growth and narrative. However, **traditional sportsbooks** remain the dominant force, leveraging established user habits, legal markets, and comprehensive product offerings to handle the vast majority of speculative wagers, with projections suggesting record-breaking betting volumes. Capital markets also react. **"Concept stocks"** in countries like South Korea and Japan experience volatile price swings based on team performance and anticipated fan spending on items like chicken, beer, and viewing parties, effectively becoming a stock market reflecting fan sentiment. The **ticket resale market** has become a sophisticated arena for arbitrage. Prices fluctuate wildly based on team draws and star power, with sellers sometimes listing tickets they don't yet own in a practice akin to short-selling, while FIFA's own "Right to Buy" tokens add another layer of speculative trading. **Collectibles and merchandise** offer another avenue. Panini sticker albums, with their inherent scarcity and nostalgic value, can become high-value collectibles. Limited-edition or locally themed jerseys command significant premiums on secondary markets, and even counterfeit vendors profit from fans' desire for affordable match-day identity. The **cryptocurrency** space has seen a frenzy of speculative, unauthorized World Cup-themed meme coins on chains like Solana. These tokens, often exploiting team names and player imagery, experience extreme pump-and-dump cycles, creating stories of massive gains for a few early entrants and steep losses for many others. Finally, an entire industry thrives on **providing information and tools** to other speculators. Developers create platforms like SeatSidekick to track ticket inventory and prices, while paid Telegram groups and subscriptions sell betting tips and predictions, monetizing the widespread desire for an informational edge. In essence, the World Cup has become a compressed, global laboratory for speculation. While the games determine champions on the field, a parallel, complex network of financial transactions—spanning prediction contracts, bets, stocks, tickets, collectibles, crypto, and information services—settles its own scores in the global market.

marsbit2h ago

Beyond the Stadium: The Profitable Games Surrounding the World Cup

marsbit2h ago

How Does Codex Use a Computer? Three Entry Points and Permission Boundaries

This article explains the three primary methods for Codex to interact with a computer, each with distinct use cases, permission boundaries, and trust levels. **1. Computer Use:** This offers the broadest access, allowing Codex to visually control and interact with the graphical user interface of authorized macOS/Windows apps, system settings, and even iOS simulators. It's ideal for tasks lacking APIs or structured tools, such as operating legacy software or multi-app workflows. However, it's the slowest method and has the widest permission scope, requiring careful supervision for sensitive actions. **2. Chrome Extension:** This grants Codex access to the user's logged-in Chrome browser state, including cookies, profiles, and open tabs. It's best for tasks requiring user identity across websites like Gmail, LinkedIn, Salesforce, or internal dashboards. Its key advantage is multi-tab control for complex workflows. While more powerful for browser-based tasks than Computer Use, it carries higher sensitivity as actions are performed under the user's identity. **3. In-App Browser:** This is a browser isolated within the Codex thread, separate from the user's personal browsing data. It excels in web development and debugging scenarios—previewing local servers, testing responsive layouts, or annotating designs directly on the page. Its isolation is a strength for development but a limitation for tasks requiring login sessions. The core principle is to choose the narrowest, safest, and most structured interface for the task. Use plugins or MCPs first, resort to visual control (Computer Use) only for GUI-dependent tasks, employ the Chrome extension for identity-reliant browser work, and prefer the In-App Browser for isolated development. **Appshots** are clarified as a fourth, complementary tool for *inputting* context—capturing a screenshot of a window to point Codex to something—rather than a method for Codex to *act*. Together, this layered approach highlights a key to AI agent productization: not granting unlimited permissions, but constraining them within clear boundaries for specific tasks while preserving user oversight.

marsbit3h ago

How Does Codex Use a Computer? Three Entry Points and Permission Boundaries

marsbit3h ago

Trading

Spot
Futures

Hot Articles

How to Buy BANANA

Welcome to HTX.com! We've made purchasing Banana Gun (BANANA) simple and convenient. Follow our step-by-step guide to embark on your crypto journey.Step 1: Create Your HTX AccountUse your email or phone number to sign up for a free account on HTX. Experience a hassle-free registration journey and unlock all features.Get My AccountStep 2: Go to Buy Crypto and Choose Your Payment MethodCredit/Debit Card: Use your Visa or Mastercard to buy Banana Gun (BANANA) instantly.Balance: Use funds from your HTX account balance to trade seamlessly.Third Parties: We've added popular payment methods such as Google Pay and Apple Pay to enhance convenience.P2P: Trade directly with other users on HTX.Over-the-Counter (OTC): We offer tailor-made services and competitive exchange rates for traders.Step 3: Store Your Banana Gun (BANANA)After purchasing your Banana Gun (BANANA), store it in your HTX account. Alternatively, you can send it elsewhere via blockchain transfer or use it to trade other cryptocurrencies.Step 4: Trade Banana Gun (BANANA)Easily trade Banana Gun (BANANA) on HTX's spot market. Simply access your account, select your trading pair, execute your trades, and monitor in real-time. We offer a user-friendly experience for both beginners and seasoned traders.

3.2k Total ViewsPublished 2024.03.29Updated 2026.06.02

How to Buy BANANA

Discussions

Welcome to the HTX Community. Here, you can stay informed about the latest platform developments and gain access to professional market insights. Users' opinions on the price of BANANA (BANANA) are presented below.

活动图片