重要なポイント

• かなり強いです。今出ている公開情報だけで言うと、GPT-5.5は「最前線級」で、特にコード生成・デバッグ、Web調査、データ分析、文書作成、ツール操作のような実務タスクで強いモデルです。[9][4]
• OpenAIの説明では、GPT-5.5は「ユーザーの意図をより速く理解し、より多くの作業を自律的に進められる」モデルで、コード、オンライン調査、データ分析、文書や表計算、ソフト操作、複数ツール横断が得意とされています。[9][4]

研究の答え

サポートビジュアル

研究に関する会話

人々も尋ねます

研究を続けてください

情報源

• [1] OpenAI Unveils Its New, More Powerful GPT-5.5 Modelnytimes.com

  Image 1: A smartphone is opened to the ChatGPT chatbot. OpenAI said its new technology was better at writing computer code and tasks related to other office work.Credit...Gabby Jones/Bloomberg Image 2: Cade Metz By Cade Metz Reporting from San Francisco April 23, 2026 See more of our coverage in your search results.Encuentra más de nuestra cobertura en los resultados de búsqueda.Add The New York Times on Google Agrega The New York Times en Google The artificial intelligence company Anthropic said this month that it would share its latest A.I. technology with only a small number of partners be…

• [2] GPT-5.5 Benchmarks Revealed: The 9 Numbers That ... - Kingy AIkingy.ai

  Kingy AI Kingy AI # GPT-5.5 Benchmarks Revealed: The 9 Numbers That Prove ChatGPT 5.5 Just Changed the AI Race Curtis Pyke by Curtis Pyke A deep, source-checked breakdown of every benchmark, capability, price point, and caveat in OpenAI’s April 23, 2026 launch of GPT-5.5 and GPT-5.5 Pro. On April 23, 2026, OpenAI officially unveiled GPT-5.5, roughly seven weeks after the launch of GPT-5.4 in early March. In The Verge’s coverage, OpenAI frames GPT-5.5 as its “smartest and most intuitive to use model yet” — a system “built to understand complex goals, use tools, check its work, and carry more t…

• [3] OpenAI announces GPT-5.5, its latest artificial intelligence modelcnbc.com

  © 2026 Versant Media, LLC. All Rights Reserved. A Versant Media Company. Data is a real-time snapshot Data is delayed at least 15 minutes. Global Business and Financial News, Stock Quotes, and Market Data and Analysis. Market Data Terms of Use and Disclaimers Data also provided byImage 16: Reuters logo This site is now part of Versant. By continuing, you agree to our Terms. You also acknowledge that our updated Privacy Policy applies, including your existing data. For info on your data rights, click “Your Privacy Choices” or see “Your Rights” in our Privacy Policy. [...] Image 3: Join Pro Liv…

• [4] OpenAI releases GPT-5.5 amid a shift to rapid-fire AI updates - Fortunefortune.com

  Fortune 500 AIOpenAI # OpenAI releases GPT-5.5 amid a shift to rapid-fire AI updates By Sharon Goldman Sharon Goldman AI Reporter By Sharon Goldman Sharon Goldman AI Reporter April 23, 2026, 2:13 PM ET OpenAI CEO Sam AltmanAnna Moneymaker/Getty Images [...] By Fortune Editors October 20, 2025 Latest in AI --- Big TechIntel Intel CEO Lip Bu Tan crushed Wall Street targets on his 1-year anniversary: We are embracing our ‘paranoid’ roots By Alexei OreskovicApril 23, 2026 17 minutes ago Big TechBillionaires ‘Don’t leave’: Jensen Huang challenges billionaire class as he insists ‘highest taxes in t…

• [5] OpenAI releases GPT-5.5 with improved coding and research capabilitiestech.yahoo.com

  AI Audio Computing Gaming Home entertainment Phones Puzzle hints Science Streaming Tech news VPN Deals More ... ## Trending: Investing.com Investing.com # OpenAI releases GPT-5.5 with improved coding and research capabilities Investing.com -- OpenAI announced Thursday the release of GPT-5.5, its latest AI model now available to Plus, Pro, Business, and Enterprise users through ChatGPT and Codex platforms. The model achieved 82.7% accuracy on Terminal-Bench 2.0, which tests command-line workflows, and 58.6% on SWE-Bench Pro, which evaluates GitHub issue resolution, according to benchmark resul…

• [6] OpenAI's GPT-5.5 is here, and it's no potato - VentureBeatventurebeat.com

  BenchmarkGPT-5.5Claude Opus 4.7Gemini 3.1 ProMythos Preview Terminal-Bench 2.082.769.4 68.5 82.0 Expert-SWE (Internal)73.1——— GDPval (wins or ties)84.980.3 67.3— OSWorld-Verified 78.7 78.0—79.6 Toolathlon55.6—48.8— BrowseComp 84.4 79.3 85.986.9 FrontierMath Tier 1–351.743.8 36.9— FrontierMath Tier 435.422.9 16.7— CyberGym 81.8 73.1—83.1 Tau2-bench Telecom (original prompts)98.0——— OfficeQA Pro54.143.6 18.1— Investment Banking Modeling Tasks (Internal)88.5——— MMMU Pro (no tools)81.2—80.5— MMMU Pro (with tools)83.2——— GeneBench25.0——— BixBench80.5——— Capture-the-Flags challenge tasks (Internal)…

• [7] Introducing GPT-5.5 - OpenAIopenai.com

  GPT‑5.5 understands what you’re trying to do faster and can carry more of the work itself. It excels at writing and debugging code, researching online, analyzing data, creating documents and spreadsheets, operating software, and moving across tools until a task is finished. Instead of carefully managing every step, you can give GPT‑5.5 a messy, multi-part task and trust it to plan, use tools, check its work, navigate through ambiguity, and keep going. [...] Notably, GPT‑5.5 shows a clear improvement over GPT‑5.4 on GeneBench⁠(opens in a new window), a new eval focusing on multi-stage scientif…

• [8] OpenAI launched GPT-5.5 on April 23, 2026, giving ChatGPT and ...threads.com

  OpenAI launched GPT-5.5 on April 23, 2026, giving ChatGPT and Codex users access to a new AI model built for coding, research, data analysis, document production and software operation. GPT-5.5 is rolling out to Plus, Pro, Business and Enterprise users in ChatGPT and Codex. GPT-5.5 Pro is available to Pro, Business and Enterprise users in ChatGPT. and the existing $200 Pro plan, aimed at heavy users and developers. Both Pro tiers differ only by usage limits: $100 Pro gives 5x Plus usage, $200 Pro gives 20x. Pro benefits include advanced GPT‑5.4 Pro reasoning, higher Codex limits, unlimited…

• [9] OpenAI launches GPT-5.5, calling it "a new class of intelligence"thenewstack.io

  Mastra empowers web devs to build AI agents in TypeScript Jan 28th 2026 11:00am, by Loraine Lawson Inferno Vet Creates Frontend Framework Built With AI in Mind Dec 10th 2025 11:00am, by Loraine Lawson JavaScript Utility Library Lodash Changing Governance Model Nov 1st 2025 7:00am, by Loraine Lawson 2026-04-23 14:04:44 OpenAI launches GPT-5.5, calling it "a new class of intelligence" Operations # OpenAI launches GPT-5.5, calling it “a new class of intelligence” The new model beats Anthropic's Opus 4.7 on most standard benchmarks. Apr 23rd, 2026 2:04pm by Frederic Lardinois Image 3: Featued ima…

• [10] With GPT-5.5, OpenAI is Making a Comeback to The Top of The AI ...trendingtopics.eu

  With GPT-5.5, OpenAI is Making a Comeback to The Top of The AI Charts Skip to content Launch # With GPT-5.5, OpenAI is Making a Comeback to The Top of The AI Charts Image 1: AvatarJakob Steinschaden, Image 2: Avatarco-written by newsrooms.ai23. April 2026, 22:34 Image 3: GPT-5.5. © OpenAI GPT-5.5. © OpenAI [...] | Benchmark | GPT-5.5 | Claude Opus 4.7 | Gemini 3.1 Pro | --- --- | | Terminal-Bench 2.0 (Coding) | 82.7% | 69.4% | 68.5% | | SWE-Bench Pro (Coding) | 58.6% | 64.3% | 54.2% | | GDPval (Knowledge Work) | 84.9% | 80.3% | 67.3% | | OSWorld-Verified (Computer Use) | 78.7% | 78.0% | – |…

• [11] A pelican for GPT-5.5 via the semi-official Codex backdoor APIsimonwillison.net

  A pelican for GPT-5.5 via the semi-official Codex backdoor API # Simon Willison’s Weblog Subscribe Sponsored by: Sonar — Now with SAST + SCA for secure, dependency-aware Agentic Engineering. SonarQube Advanced Security ## A pelican for GPT-5.5 via the semi-official Codex backdoor API 23rd April 2026 GPT-5.5 is out. It’s available in OpenAI Codex and is rolling out to paid ChatGPT subscribers. I’ve had some preview access and found it to be a fast, effective and highly capable model. As is usually the case these days, it’s hard to put into words what’s good about it—I ask it to build things…

• [12] OpenAI rolls out GPT-5.5 upgrade that's better at getting context9to5google.com

  Go to the 9to5Google home page ChatGPT OpenAI # OpenAI rolls out GPT-5.5 with improved contextual understanding, Plus and up Andrew Romero | Apr 23 2026 - 12:22 pm PT 0 Comments OpenAI just announced that ChatGPT is getting a model upgrade to GPT-5.5. The company says the model will bring better results because of changes to how it understands context. OpenAI released another lengthy press release detailing GPT-5.5. The update comes with a few changes over the previous model. It should perform significantly better across various familiar tasks, such as coding, computer use, and scientific res…

• [13] Advancing science and math with GPT-5.2 | OpenAIopenai.com

  Strong mathematical reasoning is a foundation for reliability in scientific and technical work. It enables models to follow multi-step logic, keep quantities consistent, and avoid subtle errors that can compound in real analyses—from simulations and statistics to forecasting and modeling. Improvements on benchmarks like FrontierMath reflect not a narrow skill, but stronger general reasoning and abstraction, capabilities that carry directly into scientific workflows such as coding, data analysis, and experimental design. [...] These capabilities are also closely tied to progress toward general…

• [14] GPT-5.5 is here! Available in Codex and ChatGPT todaycommunity.openai.com

  HGm8jVWbsAAwL601920×1080 485 KB HGm8jVWbsAAwL60 GPT-5.5 gets to what you are trying to do more quickly and can handle more of the work on its own. It is particularly strong at writing and debugging code, researching online, analyzing data, creating documents and spreadsheets, operating software, and working across tools until the task is complete. Instead of managing every step closely, you can hand GPT-5.5 a messy, multi-part task and rely on it to plan, use tools, verify its work, navigate ambiguity, and keep going. [...] Artificial Analysis Intelligence Index Artificial Analysis Intelligen…

• [15] GPT-5.5 System Card - Deployment Safety Hub - OpenAIdeploymentsafety.openai.com

  We measure GPT-5.5’s controllability by running CoT-Control, an evaluation suite described in (Yueh-Han, 2026 ) that tracks the model’s ability to follow user instructions about their CoT. CoT-Control includes over 13,000 tasks built from established benchmarks: GPQA (Rein et al., 2023 ), MMLU-Pro (Hendrycks et al., 2020 ), HLE (Phan et al., 2025 ), BFCL (Patil et al., 2025 [11: From tool use to agentic evaluation of large language models.” Proceedings of the 42nd international conference on machine learning . Available at: .")]) and SWE-Bench Verified. Each task is created by pairing a bench…

• [16] GPT-5.5 System Card - OpenAI Deployment Safety Hubdeploymentsafety.openai.com

  We measure GPT-5.5’s controllability by running CoT-Control, an evaluation suite described in (Yueh-Han, 2026 ) that tracks the model’s ability to follow user instructions about their CoT. CoT-Control includes over 13,000 tasks built from established benchmarks: GPQA (Rein et al., 2023 ), MMLU-Pro (Hendrycks et al., 2020 ), HLE (Phan et al., 2025 ), BFCL (Patil et al., 2025 [11: From tool use to agentic evaluation of large language models.” Proceedings of the 42nd international conference on machine learning . Available at: .")]) and SWE-Bench Verified. Each task is created by pairing a bench…

• [17] Introducing GPT-5 - OpenAIopenai.com

  Evaluations GPT‑5 is much smarter across the board, as reflected by its performance on academic and human-evaluated benchmarks, particularly in math, coding, visual perception, and health. It sets a new state of the art across math (94.6% on AIME 2025 without tools), real-world coding (74.9% on SWE-bench Verified, 88% on Aider Polyglot), multimodal understanding (84.2% on MMMU), and health (46.2% on HealthBench Hard)—and those gains show up in everyday use. With GPT‑5 pro’s extended reasoning, the model also sets a new SOTA on GPQA, scoring 88.4% without tools. _AIME results with tools sho…

• [18] Introducing GPT-5.2-Codex - OpenAIopenai.com

  GPT‑5.2‑Codex achieves state-of-the-art performance on SWE-Bench Pro and Terminal-Bench 2.0, benchmarks designed to test agentic performance on a wide variety of tasks in realistic terminal environments. It is also much more effective and reliable at agentic coding in native Windows environments, building on capabilities introduced in GPT‑5.1‑Codex‑Max. With these improvements, Codex is more capable at working in large repositories over extended sessions with full context intact. It can more reliably complete complex tasks like large refactors, code migrations, and feature builds — continuing…

• [19] Introducing gpt-oss - OpenAIopenai.com

  Keep reading View all Image 1: Hero Art Card SEO 1x1 Introducing GPT-5.5 Product Apr 23, 2026 Image 2: Making ChatGPT free for clinicians Making ChatGPT better for clinicians Product Apr 22, 2026 Image 3: OAI Blog Agents Hero 1x1 Introducing workspace agents in ChatGPT Product Apr 22, 2026 Our Research Research Index Research Overview Research Residency Economic Research Latest Advancements GPT-5.5 GPT-5.4 GPT-5.3 Instant GPT-5.3-Codex Safety Safety Approach Security & Privacy Trust & Transparency ChatGPT Explore ChatGPT(opens in a new window) Business Enterprise Education Pricing(opens in…

• [20] Introducing GPT-5.4 | OpenAIopenai.com

  GPT‑5.4 brings together the best of our recent advances in reasoning, coding, and agentic workflows into a single frontier model. It incorporates the industry-leading coding capabilities of GPT‑5.3‑Codex⁠ while improving how the model works across tools, software environments, and professional tasks involving spreadsheets, presentations, and documents. The result is a model that gets complex real work done accurately, effectively, and efficiently—delivering what you asked for with less back and forth. [...] > “GPT-5.4 is the best model we’ve ever tried. It’s now top of the leaderboard on our…

• [21] OpenAI Research | Releaseopenai.com

  Product Mar 5, 2026 Introducing GPT-5.4 Introducing GPT-5.4, OpenAI’s most most capable and efficient frontier model for professional work, with state-of-the-art coding, computer use, tool search, and 1M-token context. Product Mar 3, 2026 GPT-5.3 Instant: Smoother, more useful everyday conversations Product Feb 12, 2026 Introducing GPT-5.3-Codex-Spark Introducing GPT-5.3-Codex-Spark—our first real-time coding model. 15x faster generation, 128k context, now in research preview for ChatGPT Pro users. Product Feb 5, 2026 Introducing GPT-5.3-Codex GPT-5.3-Codex is a Codex-native agent that pairs…

• [22] GPT-5 is here - OpenAIopenai.com

  Everyone can be a power user ChatGPT thinks harder on complex tasks and asks relevant follow-up questions to keep work moving. Every employee can get expert-level results without switching models. See how businesses use GPT-5 Image 23: GPT-5 works with connectors Smarter with your company context GPT‑5 produces higher-quality responses by using your company’s files and connected apps like Google Drive, SharePoint, and more, while respecting existing permissions. Explore apps(opens in a new window) ## Get started with GPT‑5 Try now(opens in a new window) Our Research Research Index Research Ov…

• [23] GPT-5.5 System Card - Deployment Safety Hub - OpenAIdeploymentsafety.openai.com

  GPT-5.4 Thinking production data and resampled data with the same model on the same distribution. [...] ## 3.1.1 Evaluations with Challenging Prompts We conducted benchmark evaluations across disallowed content categories. We report here on our Production Benchmarks, an evaluation set with conversations representative of challenging examples from production data. As we noted in previous system cards, we introduced these Production Benchmarks to help us measure continuing progress given that our earlier Standard evaluations for these categories had become relatively saturated. [...] Table 1. P…