Passer au contenu principal
OpenAI

2 février 2025

Versions

Présentation de la recherche approfondie

Un agent qui utilise le raisonnement pour synthétiser de grandes quantités d’informations en ligne et mener des tâches de recherche complexes à votre place. Disponible dès aujourd’hui pour les utilisateurs Pro, bientôt pour Plus et Team.

Chargement…

Mise à jour du 10 février 2026 : Vous pouvez désormais connecter la recherche approfondie à n’importe quel MCP ou application et limiter les recherches Web à des sites de confiance, afin de vous concentrer sur des sources authentifiées et conformes aux normes du secteur. Vous pouvez également suivre la progression en temps réel et interrompre pour affiner avec des invites de suivi ou de nouvelles sources. Nous avons mis à jour l’expérience visuelle pour qu’il soit plus facile de démarrer, de suivre et de passer en revue votre recherche de bout en bout.


Mise à jour du 17 juillet 2025 : La recherche approfondie peut désormais aller encore plus loin et plus large grâce à l'accès à un navigateur visuel intégré à l'agent ChatGPT. Pour accéder à ces capacités mises à jour, sélectionnez simplement « mode agent » dans le menu déroulant du compositeur et saisissez votre requête directement. La fonctionnalité originale de recherche approfondie reste disponible via l'option « recherche approfondie » dans le menu des outils.


Mise à jour du 24 avril 2025 : Nous augmentons considérablement la fréquence d'utilisation de la recherche approfondie—les utilisateurs des versions Plus, Team, Enterprise et Edu bénéficient désormais de 25 requêtes par mois, les utilisateurs Pro de 250 et les utilisateurs Free de 5. Ceci est rendu possible grâce à une nouvelle version allégée de la recherche approfondie, propulsée par une version d'o4-mini, conçue pour être plus économique tout en conservant une qualité optimale. Une fois votre limite atteinte pour la version complète, vos requêtes basculeront automatiquement vers la version allégée.


Mise à jour du 25 février 2025 : Tous les utilisateurs Plus peuvent désormais utiliser la recherche approfondie.


Mise à jour du 5 février 2025 : La recherche approfondie est désormais accessible aux utilisateurs Pro au Royaume-Uni, en Suisse et dans l’Espace économique européen.


Aujourd’hui, nous lançons la recherche approfondie dans ChatGPT, une nouvelle capacité agentique qui effectue des recherches en plusieurs étapes sur Internet pour des tâches complexes. Il exécute en quelque dizaines de minutes ce qui prendrait plusieurs heures à un être humain.

La recherche approfondie est le prochain agent d’OpenAI qui peut travailler pour vous de manière autonome : il vous suffit de lui donner une invite, et ChatGPT trouvera, analysera et synthétisera des centaines de sources en ligne pour créer un rapport complet digne d’un analyste de recherche. Optimisée pour une navigation web et pour l’analyse de donnée, elle repose sur une version future du modèle OpenAI o3, et s’appuie sur le raisonnement pour rechercher, interpréter et analyser de larges volumes de textes, d’images et de PDF sur Internet, en s’adaptant si nécessaire en fonction des informations recueillies.

La capacité à synthétiser les connaissances est un prérequis pour la création de nouvelles connaissances. Pour cette raison, la recherche approfondie marque une étape importante vers notre objectif plus large de développement de l'AGI, que nous envisageons depuis longtemps comme capable de produire des recherches scientifiques novatrices.

Why we built deep research

Deep research is built for people who do intensive knowledge work in areas like finance, science, policy, and engineering and need thorough, precise, and reliable research. It can be equally useful for discerning shoppers looking for hyper-personalized recommendations on purchases that typically require careful research, like cars, appliances, and furniture. Every output is fully documented, with clear citations and a summary of its thinking, making it easy to reference and verify the information. It is particularly effective at finding niche, non-intuitive information that would require browsing numerous websites. Deep research frees up valuable time by allowing you to offload and expedite complex, time-intensive web research with just one query.

Deep research independently discovers, reasons about, and consolidates insights from across the web. To accomplish this, it was trained on real-world tasks requiring browser and Python tool use, using the same reinforcement learning methods behind OpenAI o1, our first reasoning model. While o1 demonstrates impressive capabilities in coding, math, and other technical domains, many real-world challenges demand extensive context and information gathering from diverse online sources. Deep research builds on these reasoning capabilities to bridge that gap, allowing it to take on the types of problems people face in work and everyday life.

How to use deep research

In ChatGPT, select ‘deep research’ in the message composer and enter your query. Tell ChatGPT what you need—whether it’s a competitive analysis on streaming platforms or a personalized report on the best commuter bike. You can attach files or spreadsheets to add context to your question. Once it starts running, a sidebar appears with a summary of the steps taken and sources used.

Deep research may take anywhere from 5 to 30 minutes to complete its work, taking the time needed to dive deep into the web. In the meantime, you can step away or work on other tasks—you’ll get a notification once the research is complete. The final output arrives as a report within the chat – in the next few weeks, we will also be adding embedded images, data visualizations, and other analytic outputs in these reports for additional clarity and context.

Compared to deep research, GPT‑4o is ideal for real-time, multimodal conversations. For multi-faceted, domain-specific inquiries where depth and detail are critical, deep research’s ability to conduct extensive exploration and cite each claim is the difference between a quick summary and a well-documented, verified answer that can be usable as a work product.

GPT-4o

Help me find iOS and android adoption rates, % who want to learn another language, and change in mobile penetration, over the past 10 years, for top 10 developed and top 10 developing countries by GDP. Lay this info out in a table and separate stats into columns, and include recommendations on markets to target for a new iOS translation app from ChatGPT, focusing on markets ChatGPT is currently active in.

Compiling comprehensive data on iOS and Android adoption rates, the percentage of populations interested in learning another language, and changes in mobile penetration over the past decade for the top 10 developed and developing countries by GDP is challenging due to data limitations. However, based on available information, we can provide insights and recommendations for targeting markets with a new iOS translation app powered by ChatGPT.

Top 10 Developed Countries by GDP:

  1. United States
  2. Japan
  3. Germany
  4. United Kingdom
  5. France
  6. Italy
  7. Canada
  8. South Korea
  9. Australia
  10. Spain

Top 10 Developing Countries by GDP:

  1. China
  2. India
  3. Brazil
  4. Russia
  5. Indonesia
  6. Mexico
  7. Turkey
  8. Saudi Arabia
  9. Argentina
  10. South Africa

Insights:

  • iOS and Android Adoption Rates: Globally, Android holds a dominant market share of approximately 70.93%, while iOS accounts for about 28.32% as of 2024. In the United States, iOS leads with a 58.81% market share. Other developed countries like Japan, Canada, Australia, and the United Kingdom also show a higher preference for iOS devices. In contrast, developing countries such as India and Brazil have a higher prevalence of Android devices.
  • Interest in Language Learning: While specific percentages of populations interested in learning another language are not readily available, the global popularity of language learning apps like Duolingo, which had approximately 14.3 million downloads in July 2024, indicates a significant interest. This interest is likely higher in countries with diverse linguistic landscapes or where English is not the primary language.
  • Mobile Penetration Over the Past Decade: Mobile phone ownership has seen substantial growth globally. In the United States, smartphone ownership increased from 35% in 2011 to 91% in 2024. Developing countries have also experienced significant growth in mobile penetration, contributing to increased access to digital services.

Recommendations:

Considering the available data and focusing on markets where ChatGPT is currently active, the following developed countries are promising targets for a new iOS translation app:

  • United States: High iOS market share and significant interest in language learning.
  • United Kingdom: Substantial iOS user base and a multicultural population with diverse language needs.
  • Canada: Notable iOS adoption and a bilingual population (English and French), increasing the demand for translation services.

Among developing countries, the following are noteworthy:

  • China: Despite Android's dominance, the large population and growing interest in English and other languages present a significant opportunity.
  • India: High Android usage, but a growing middle class with increasing iOS adoption and a strong interest in language learning, especially English.
  • Brazil: Predominantly Android users, but with a sizable market for language learning apps, particularly for English and Spanish.

Focusing on these markets aligns with ChatGPT's current availability and leverages existing mobile adoption trends and language learning interests.

Deep research

Help me find iOS and android adoption rates, % who want to learn another language, and change in mobile penetration, over the past 10 years, for top 10 developed and top 10 developing countries by GDP. Lay this info out in a table and separate stats into columns, and include recommendations on markets to target for a new iOS translation app from ChatGPT, focusing on markets ChatGPT is currently active in.

Top 10 Developed Economies (by GDP)Smartphone OS Share, Language-Learning Interest, and Mobile Penetration Growth

Country

iOS Market Share

Android Market Share

Interest in New Language

(% of population)

Mobile Penetration Change (2013→2023)

United States

(USA)

~58% iOS vs 42% Android

(see left)

High:

70% regret losing foreign-language ability (indicating strong desire to improve)

56%→82%

smartphone penetration (↑26 pp)

Japan

~69% iOS vs 31% Android

(see left)

High:

Over 50% want to learn English

~30%→79%

(approx.) (↑~50 pp)

Germany

~39% iOS vs 60% Android

(see left)

High:

86% of Europeans say everyone should speak ≥1 foreign language (strong pro-language attitude)

40%→82%

(↑42 pp)

United Kingdom

(UK)

~52% iOS vs 47% Android

(see left)

Moderate-High:

~73% have some interest (only 27% “no interest” in new languages)

62%→82%

(↑20 pp)

France

~35% iOS vs 64% Android

(see left)

High:

86% (EU average) favor multilingualism; English widely seen as important

42%→83%

(↑40 pp)

Italy

~30% iOS vs 69% Android

(see left)

High:

86% (EU avg.) favor language learning; 1 in 4 regret not learning another

41%→85%

(↑44 pp)

Canada

~60% iOS vs 40% Android

(see left)

Moderate:

Many bilingual (English/French); rising interest in third languages (no recent % data)

56%→~80%

(↑ ~24 pp) (est., similar to US)

South Korea

~24% iOS vs 76% Android

(see left)

Moderate:

Strong English education focus; ~40% of teens are learning English

73%→~95%

(↑ ~22 pp) – already very high by 2013 (near saturation now)

Australia

~55% iOS vs 45% Android

(see left)

Moderate:

~70% see learning languages as valuable (English dominant but interest in Asian languages growing)

65%→~85%

(↑ ~20 pp) (est., high smartphone use)

Spain

~20% iOS vs 79% Android

(see left)

High:

88% of Spaniards learned a foreign language in school (e.g. English); strong cultural interest

55%→~85%

(↑ ~30 pp) (est., nearing Western Europe peers)

Top 10 Developing/Emerging Economies (by GDP)(ChatGPT availability considered)

Country

iOS Market Share

Android Market Share

Interest in New Language

(notable stats)

Mobile Penetration Change (2013→2023)

China

^(ChatGPT restricted)

~24% iOS vs 75% Android

(see left)

Very High:

Hundreds of millions learning English (but ChatGPT not officially accessible)

47%→68%

(↑21 pp)

India

~4% iOS vs 95% Android

(see left)

High:

English compulsory in many schools; strong economic motivation (80% link English to higher income)

~5%→46%

(↑ ~41 pp) (huge jump in smartphone adoption)

Brazil

~18% iOS vs 82% Android

(see left)

High:

Great demand for English – only ~5% speak it, but most see it as key skill

26%→67%

(↑40 pp)

Russia

^(ChatGPT limited)

~30% iOS vs 69% Android

(see left)

Moderate:

English learning common (compulsory in school); interest exists but ChatGPT availability is uncertain

36%→74%

(↑38 pp)

Mexico

~24% iOS vs 76% Android

(see left)

High:

Strong desire to learn English for US job/migration; ~50% of students study English in school (est.)

37%→62%

(↑25 pp)

Indonesia

~12% iOS vs 88% Android

(see left)

High:

English seen as gateway skill; government programs to improve English proficiency

<30%→68%

(↑ ~40 pp)

Turkey

~15% iOS vs 85% Android (est.)

(see left)

High:

English highly valued (universal in education);

80%

link English to better jobs

30%→75%

(↑45 pp)

Saudi Arabia

~24% iOS vs 76% Android

(see left)

Moderate:

English widely taught; 92% smartphone ownership (many already bilingual in English/Arabic)

73%→~95%

(↑ ~22 pp) (early adopter; near saturation now)

South Africa

~16% iOS vs 83% Android

(see left)

High:

Multilingual society; English and Afrikaans taught alongside native languages – cultural impetus to learn others

40%→~60%

(↑ ~20 pp) (est., steady growth)

Argentina

~12% iOS vs 88% Android

(see left)

High:

Strong interest in English (Argentina leads Latin America in English proficiency)

31%→~70%

(↑ ~39 pp) (est., sharp rise with smartphone adoption)

Sources: Smartphone OS shares are from StatCounter/Statista data (2023–24). Language-interest metrics come from surveys by Preply, Eurobarometer, Babbel, etc. (e.g. UK 73% interest; US 70% regret lack of languages; Japan >50% want English; Pearson global survey). Mobile penetration is measured as smartphone ownership percentage – dramatic growth is noted in developing markets (e.g. Brazil +40 points) and high saturation in developed ones (e.g. UK ~82%) over the last decade.


Recommendations: Based on the above, prime targets for a new ChatGPT‑powered iOS translation app would be countries with large iOS user bases and strong language-learning demand, where ChatGPT is accessible. Notably, Japan, the U.S., UK, Canada, and Australia emerge as top choices. These markets pair high iOS adoption (50–60%+ share) with significant enthusiasm for language learning – for example, Japan’s iPhone dominance and widespread desire to learn English make it ideal. English-speaking countries like the US, UK, Canada, and Australia, despite being monolingual societies, show substantial interest in learning other languages (e.g. Spanish or French), and all have over 80% smartphone penetration and millions of iPhone users.

Among emerging economies, Mexico and Brazil stand out as secondary targets: although Android prevails, their sheer population sizes mean tens of millions of iPhone users exist, and interest in English is very high for career and education reasons. These Latin American markets (where ChatGPT is active) could yield strong adoption for an iOS-only app, especially given the motivation to learn English. Conversely, China and Russia are less feasible – China’s OS split skews Android and ChatGPT is not officially available there, and Russia faces access and regulatory uncertainties.

In summary, focus on iOS-heavy, pro-learning markets: Japan and Western countries (US, UK, Canada, Australia, plus high-income Europe like Germany and France to a lesser degree) should be the first-tier targets. They combine robust iOS usage with favorable language-learning attitudes. A second tier includes large-population developing markets (Mexico, Brazil, perhaps Saudi Arabia for its historically high iPhone uptake) where interest in English is strong – these can be approached once the app gains traction in the primary markets. Such a strategy ensures the app launches where it has the greatest alignment of platform (iOS) presence and user demand for translation/language tools, maximizing the likelihood of adoption and growth.

Deep research responds to the prompt in a highly detailed manner, providing side-by-side country-specific data for both top 10 developed and top 10 developing countries for easy reference and comparison. It uses that information to offer detailed market-entry recommendations that are informed and usable.

Comment ça marche?

La recherche approfondie a été formée à l'aide d'un apprentissage par renforcement de bout en bout sur des tâches complexes de navigation et de raisonnement dans divers domaines. Grâce à cette formation, elle a appris à planifier et à exécuter une trajectoire en plusieurs étapes pour trouver les données dont elle a besoin, en revenant sur ses pas et en réagissant aux informations en temps réel si nécessaire. Le modèle est également capable de parcourir les fichiers téléversés par les utilisateurs, de tracer et de reproduire des graphiques à l’aide de l’outil Python, d’intégrer dans ses réponses des graphiques générés ainsi que des images provenant de sites Web, et de citer des phrases ou des passages spécifiques de ses sources. Grâce à cette formation, il atteint de nouveaux records dans le cadre d’un certain nombre d’évaluations publiques axées sur des problèmes concrets.

Humanity's Last Exam

Dans Humanity’s Last Exam(s'ouvre dans une nouvelle fenêtre), une évaluation récemment publiée qui teste l'IA sur un large éventail de sujets avec des questions de niveau expert, le modèle alimentant la recherche approfondie atteint un nouveau sommet avec une précision de 26,6 %. Ce test consiste en plus de 3 000 questions à choix multiples et à des réponses courtes portant sur plus de 100 sujets, de la linguistique à l’astronautique, des lettres classiques à l’écologie. Comparativement à OpenAI o1, les avancées majeures ont été observées dans les domaines de la chimie, des sciences humaines et sociales et des mathématiques. Le modèle qui alimente la recherche approfondie imite l’approche humaine en recherchant efficacement des informations spécialisées lorsque cela s’avère nécessaire.

ModèlePrécision (%)
GPT-4o3,3
Grok-23,8
Claude 3.5 Sonnet4,3
Gemini avec réflexion6,2
OpenAI o19,1
DeepSeek-R1*9,4
OpenAI o3-mini (intermédiaire)*10,5
OpenAI o3-mini (élevé)*13,0
Recherche approfondie OpenAI**26,6
* Ce modèle n’est pas multimodal et l’évaluation a donc porté sur un sous-ensemble composé de texte uniquement.
** avec navigation + outils Python

GAIA

Sur GAIA(s'ouvre dans une nouvelle fenêtre)1, une référence publique qui évalue l'IA sur des questions concrètes, le modèle qui alimente la recherche approfondie atteint un nouveau niveau de pointe (SOTA), se classant en tête du classement(s'ouvre dans une nouvelle fenêtre) externe. Comprenant des questions de trois niveaux de difficulté, la réussite de ces tâches requiert des compétences telles que le raisonnement, la maîtrise multimodale, la navigation Web et la maîtrise des outils.

GAIA
Niveau 1Niveau 2Niveau 3Moy.
État de l’art précédent(s'ouvre dans une nouvelle fenêtre)67,9267,4442,3163,64
Recherche approfondie (pass@1)74,2969,0647,667,36
Recherche approfondie (cons@64)78,6673,2158,0372,57

Exemples de tâches GAIA

In Nature journal's Scientific Reports conference proceedings from 2012, in the article that did not mention plasmons or plasmonics, what nano-compound is studied? Don't use the prefix nano in your answer if there is one.

[The remaining Chain-of-Thought messages and the final answer are hidden to protect the benchmark's ground truth answer.]

Clarifying the search

I’m piecing together the request for an article from 2012 in Scientific Reports that details a nano-compound, excluding any related to plasmonics. Likely, this involves filtering specific topics or compounds, like silver or graphene.

Piecing together details

I'm sub-searching "Scientific Reports 2012 nanoparticle," likely seeking nano-compounds. Interested in filtering out plasmon-related topics, possibly focusing on silver, graphene, or quantum dots.

[action de recherche]

Navigating search filters

I’m digging into advanced search filters on nature.com and Scientific Reports for 2012, trying to pinpoint articles on amorphous carbon nanoparticles in food caramels.

Identifying conference proceedings

The search results reveal a conference proceeding titled "2D quasiperiodic plasmonic crystals" from 2012, likely found under the "Conference Proceedings" category in Scientific Reports.

[navigation d’action]

Reflecting on potential issues

I'm considering the reasons behind a web page misconception, likely due to an outdated agent type or inadvertent blockage.

[navigation d’action]

Considering dynamic options

I'm thinking about a nature site with dynamic content or a cached version. Alternatively, trying a search for specific phrases might help.

[action de recherche]

Pinpointing key features

OK, I'm identifying four conference proceedings from 2012 in Sci Rep. Notably, some mention "plasmonic" and should be excluded.

[navigation d’action]

Piecing together insights

I’m gathering info on accessing cached versions or snippet expansions for specific titles to ensure comprehensive analysis.

[action de recherche]

Pulling together the details

I’m noting the progression from the 2012 European Materials Research Society Spring Meeting to the scientific report, focusing on conference proceedings. This approach helps establish context and relevance.

[action de recherche]

Tracking journal clues

Trying to connect conference proceedings from late 2012 with "Scientific Reports" journal, focusing on plasmonic 2D quasiperiodic materials. This approach feels methodical and precise.

[action de recherche]

Analyzing event details

Noting that the search results [8] include a page likely summarizing the European Materials Research Society 2012 Spring Meeting, including 25 symposia.

[navigation d’action]

Piecing together research

I’m examining a likely collection page with 4 articles, considering plasmonic and metamaterial topics, and identifying key references from the European Materials Research Society 2012 Spring Meeting.

[navigation d’action]

Pinpointing the focus

I’m focusing on the 2012 conference proceedings in "Scientific Reports" from E-MRS, likely involving topics like "2D quasiperiodic plasmonic crystals" and "Layered plasmonic cloaks to tailor the optical scattering at the nanoscale."

[navigation d’action]

Evaluating library sources

Thinking about special issue E-MRS 2012 Sci rep invited paper Monticone and metamaterials lab at News Archives – 2012.

[navigation d’action]

Assessing accessibility

I'm gathering info on potential site access issues, considering outdated status or blockages. Also, evaluating the Monticone site for a list reference.

[navigation d’action]

Piecing together E-MRS 2012

I'm trying to link "Layered Plasmonic Cloaks" to E-MRS 2012. Considering other possible topics like graphene and catalysis.

[navigation d’action]

Identifying relevant topics

I’m gathering info on topics like graphene, photovoltaics, and nanostructured compounds, while excluding plasmonic-related ones. This leads me to focus on nanotechnology aspects more broadly.

[navigation d’action]

Adjusting my focus

I’m broadening the search parameters by entering specific site and scholar identifiers to pinpoint articles about 2D quasiperiodic plasmonic crystals in Nature Scientific Reports from 2012.

[action de recherche]

Identifying non-plasmonic possibilities

I'm narrowing down the search to identify articles from the 2012 E-MRS special issue in Scientific Reports. This involves checking titles for non-plasmonic topics, like graphene or functional oxides. Progress is evident through focused searches and exclusion of plasmonic articles.

[action de recherche]

Piecing together clues

I'm analyzing interactions in a graphene superlattice, likely from a Sci Rep article. Considering titles by authors like Padooru, Yakovlev, Chen, and Alu.

[action de recherche]

Piecing together the puzzle

I’m gathering info on E-MRS 2012 Spring Meeting's Sci Rep proceedings, focusing on invited papers, without plasmonic phenomena. Types under review are graphene, catalysis, energy materials, nanomedicine, and sensors.

[action de recherche]

Tâches de niveau expert

Lors d'une évaluation interne de tâches de niveau expert dans divers domaines, la recherche approfondie a été jugée par les experts du domaine comme ayant automatisé plusieurs heures d'enquête manuelle difficile. 

Taux de réussite en fonction du nombre maximal d’appels à l’outil
Taux de réussiteNombre maximal d’appels à l’outil
Plus le modèle navigue et réfléchit à ce qu'il navigue, plus il est performant. C'est pourquoi il est important de lui laisser le temps de réfléchir.
Exemples de tâches de niveau expert
Temps économisé sur la tâche : 4 heures

I am a researcher interested in bringing mixed-gas sorption capabilities to my lab. Please discuss the differences between pure- and mixed-gas sorption for glassy polymers, how the dual-mode sorption model can be used to predict mixed-gas sorption behavior in glassy polymers (include equations where applicable), and what challenges there are in accurately predicting pure- and mixed-gas sorption using the dual-mode sorption model. Only include open-source information as of October 1, 2024.

Pure vs. mixed-gas sorption in glassy polymers: In a glassy polymer (below TgT_g), a single gas typically exhibits a concave sorption isotherm: uptake rises sublinearly with pressure, unlike the linear Henry’s-law behavior above TgT_g. This is attributed to “dual-mode” sorption: some penetrant dissolves in the dense polymer matrix (obeying Henry’s law) while additional penetrant saturates specific microvoid “sites” (a Langmuir-type adsorption in the polymer’s nonequilibrium free volume). By contrast, when two or more gases are present, they compete for those limited Langmuir sorption sites. As a result, each component’s sorbed concentration in a mixture is generally lower than it would be at the same partial pressure alone. In particular the less soluble (lower-affinity) gas tends to be more strongly suppressed, often causing the mixed-gas solubility selectivity (ratio of concentrations) to exceed the ideal value predicted from pure-gas isotherms. For example, in CO₂/CH₄ mixtures both components sorb less than in their pure-gas cases (especially CH₄), so the CO₂/CH₄ sorption selectivity is higher under mixture conditions. In extreme cases, mixed-gas effects can even reverse performance trends observed with single gases. (We note that unlike competitive sorption, synergistic sorption – where one gas increases the sorption of another via polymer swelling – is usually minor in rigid high-free-volume polymers under moderate pressures.)

Dual-mode sorption model and mixed-gas prediction: The dual-mode sorption (DMS) model quantitatively captures glassy polymer sorption by superposing a Henry’s-law term and a Langmuir term. For a single gas, the sorbed concentration CC (e.g. in cm³(STP) gas per cm³ polymer) is written as:

C(p)=kDp  +  CHbp1+bp.C(p) = k_D\,p \;+\; \frac{C'_H\,b\,p}{\,1 + b\,p\,}\,.

Here kDk_D is the Henry’s law coefficient for dissolution, CHC'_H is the Langmuir capacity constant (proportional to the polymer’s unrelaxed free-volume or “hole” capacity), and bb is the Langmuir affinity constant. This empirical formula yields the characteristic concave isotherm of glassy polymers and reduces to simple Henry’s law at the glass-transition (since CH0C'_H \to 0 as TTgT \to T_g). The same three parameters (kD,CH,bk_D, C'_H, b) are obtained by fitting pure-gas sorption data and are then used to predict mixture sorption. For a binary mixture of gases A and B (with partial pressures pA,pBp_A, p_B), the DMS model assumes each gas obeys its own Henry’s term and that both compete for the same Langmuir sites. One convenient form is to write the total sorbed concentration as the sum of contributions from each gas:

Ctot=kD,ApA+kD,BpB  +  CH,AbApA  +  CH,BbBpB1+bApA+bBpB,C_{\text{tot}} = k_{D,A}p_A + k_{D,B}p_B \;+\; \frac{\,C'_{H,A}\,b_A\,p_A \;+\; C'_{H,B}\,b_B\,p_B\,}{\,1 + b_A p_A + b_B p_B\,}\,,

which implicitly means the concentration of component i in the mixture is Ci=kD,ipi+CH,ibipi1+jbjpjC_i = k_{D,i} p_i + \frac{C'_{H,i} b_i p_i}{\,1+\sum_j b_j p_j\,}. This reduces to the single-gas formula when the other component’s pressure is zero. In practice, partial pressure in these equations is often replaced by fugacity for accuracy at high pressures, though using fugacities or pressures gives nearly the same results if applied consistently. The DMS mixed-gas model predicts the competitive sorption effect observed experimentally – namely, each gas’s uptake is depressed relative to its pure-gas sorption isotherm.

Challenges and limitations: Although the dual-mode model is widely successful in correlating sorption data, it has notable limitations in predicting sorption behavior. First, the DMS model is empirical – its fitted parameters are not universal constants but can vary with polymer formation history, physical aging, and temperature/pressure range. This means a parameter set obtained under one set of conditions may lack predictive power outside its calibration range. For instance, sorption isotherms measured only over a limited pressure range can be fit well by DMS, but extrapolating beyond that (especially approaching plasticization pressures) may be unreliable. Indeed, multiple distinct combinations of kDk_D, CHC'_H, bb can sometimes fit the same pure-gas isotherm almost equally well – yet they yield markedly different mixed-gas predictions. This sensitivity undermines confidence in mixture forecasts, as one study showed that using different pure-gas fit sets led to only qualitative agreement with some mixed-CO₂/CH₄ data.

Furthermore, DMS inherently assumes a fixed population of Langmuir sites (microvoids) and ignores polymer relaxation or swelling induced by sorbate. In reality, penetrant-induced swelling (plasticization) can increase free volume and sorption capacity, especially for highly condensable gases at high activity – an effect the basic DMS model cannot capture. In binary sorption, this means any synergistic increase in sorption due to a second gas (or due to polymer dilation) is unaccounted for in the standard model. Conversely, the model also cannot describe sorption isotherm shapes that deviate from concave Langmuir-type behavior (e.g. sigmoidal isotherms caused by specific polymer-penetrant interactions or clustering). For example, glassy polymers absorbing polar molecules like alcohols can show sigmoidal sorption isotherms, which the simple dual-mode framework fails to represent. Finally, accurately measuring mixed-gas sorption itself is challenging, and discrepancies between idealized model assumptions (e.g. truly zero downstream pressure, no competitive diffusion limitations) and experimental realities can add to prediction error. Despite these challenges, the dual-mode sorption model – with appropriate care – remains a valuable first approximation for interpreting sorption in glassy polymers, and it highlights the key role of competitive site occupancy in mixed-gas environments. Researchers often turn to more elaborate models (e.g. non-equilibrium lattice fluid or thermodynamic theories) when the dual-mode model’s assumptions break down, but such models come at the cost of additional parameters or complexity. In summary, dual-mode sorption provides a useful baseline for pure- and mixed-gas sorption in glassy polymers, but one must be mindful of its empirical nature and the above limitations when predicting multicomponent sorption behavior in practice.

Sources: Dual-mode sorption model and mixed-gas extension; competitive sorption effects in mixtures; model equations and parameters; limitations of DMS model; parameter sensitivity and predictivity issues.

Comprendre les modèles de sorption

Je recueille des informations sur la sorption de gaz purs et mixtes dans les polymères vitreux, en me concentrant sur le modèle de sorption à double mode et en abordant les défis liés aux prédictions de modélisation.

[action de recherche]

Évaluation de l’accès libre

D'accord, laisse-moi voir. Le résultat de MDPI sur la sorption de gaz mixtes dans les polymères vitreux est probablement en accès libre.

[navigation d’action]

[navigation d’action]

Examen des sections
Je rassemble des informations issues du modèle de sorption à double mode et de son analyse approfondie dans l'article de MDPI.

[navigation d’action]

Clarification des propriétés clés

J’examine le rapport de laboratoire pour comprendre la constante de la loi de Henry, la constante d’affinité de Langmuir et la constante de capacité de Langmuir, qui décrivent la sorption des gaz.

[navigation d’action]

Assembler

J'examine la possibilité que « Équation (3) » et « Équation (4) » soient des images ou des affichages de formules, et j'envisage de consulter le PDF ou de chercher des références antérieures pour mieux les comprendre.

[navigation d’action]

Confirmation de la pertinence du titre

Je vérifie si le document de Freeman et Koros (1980) correspond précisément à la référence « Model for sorption of mixed gases in glassy polymers » en vérifiant son résumé et son titre.

[action de recherche]

Examiner les liens entre les articles

J'ai remarqué que le résultat provenant de « pmc.ncbi.nlm.nih.gov » est probablement le même article MDPI, et je suis curieux de voir s'il présente le texte complet ou une version simplifiée.

[navigation d’action]

[navigation d’action]

[navigation d’action]

Collecte d'informations

Je recueille des informations sur la sorption de gaz purs et mixtes dans les polymères vitreux. C'est une étape cruciale pour comprendre le comportement du matériau dans différents environnements gazeux.

[action de recherche]

Comparaison de la sorption des gaz

J'ai remarqué que la présence de dioxyde de carbone dans un mélange affecte la sorption du méthane dans le polymère, réduisant la sorption du méthane par rapport à un scénario de gaz pur.

[navigation d’action]

Relier des concepts

Je réfléchis à la manière dont le terme « mélange d'équations à double mode étendu » pourrait être lié aux équations des câbles supraconducteurs à double mode. Cela montre un potentiel pour connecter des concepts à travers différents domaines.

[action de recherche]

Demande des détails de la révision

Je prends note de la demande de vérification de « Theories of Sorption and Transport in Polymer Membrane ».

[navigation d’action]

Vérification du lien PDF

Je m’intéresse au Résultat [2] et j’explore l’extrait, qui consiste à étendre un modèle d’adsorption à double mode à un mélange binaire et à exprimer la concentration de A en fonction des pressions partielles et des constantes.

[action de recherche]

Prédiction du comportement de sorption

Le modèle à double mode prévoit que l’ajout d’un second gaz réduit la sorption à pression partielle constante, contrairement aux scénarios de gaz pur.

[navigation d’action]

Récupération d’un PDF

Je rassemble des informations à partir d’un PDF sur nature.com, possiblement un ancien article de Yampol'ski, mais je pense aussi à des sources alternatives comme le dépôt de l’Université du Texas à Austin pour un extrait de texte.

[navigation d’action]

Évaluer les options de dépôt

J’ai constaté que les résultats du dépôt UT peuvent ne pas s’afficher correctement. La recherche à l'intérieur est incertaine. Alternativement, le résultat [3] contient un extrait décrivant le modèle de sorption par mélange à double mode, expliquant les effets de compétition et son adéquation pour modéliser les données expérimentales.

[action de recherche]

Affiner le focus

J'ajuste mon approche pour m'assurer que la recherche cible le bon contexte.

[action de recherche]

Comprendre les modèles de sorption

Je détaille le modèle de sorption à double mode pour les gaz purs : dissolution selon Henry et remplissage des microvides selon Langmuir. Pour les gaz mélangés, la sorption compétitive et les comportements non idéaux sont mises en évidence.

[action de recherche]

Explorer hero.epa.gov

Réfléchir au résumé ou au contenu potentiel du site hero.epa.gov.

[navigation d’action]

Affiner le modèle

Je recueille des informations sur la sorption de gaz pur et de gaz mélangé, en tenant compte de facteurs tels que la compétition, la plasticisation et la stabilité des paramètres. Intégration des données sur les gaz mélangés pour des prédictions plus précises.

[navigation d’action]

Aborder les défis du modèle de sorption double

Le couplage des paramètres et la non-unicité ont un impact sur les prédictions. L'absence de modifications des conditions du polymère peut entraîner des oublis.

[navigation d’action]

Quantification de la déviation

Je quantifie la solubilité non idéale du CO2-CH4 dans le 6FDA-mPDA, montrant les effets des gaz mélangés sur la solubilité. La sorption compétitive n’est pas la seule cause de la diminution de la sélectivité de perméabilité.

[navigation d’action]

Intégration des références

Je rassemble des citations, en me concentrant sur des documents en libre accès comme MDPI 2019 et Vopicka 2014, pour soutenir la discussion sur les différences et les défis du modèle à double mode pour la sorption de gaz dans les membranes polymériques.

[navigation d’action]

Proposer des sections

J'organise des sections sur la sorption de gaz pur versus gaz mélangé, j'explore le modèle de sorption à double mode, et je détaille des défis tels que l'incertitude des paramètres et la prédiction des gaz mélangés.

Organisation du contenu

Je me concentre sur le modèle d'adsorption à double mode, en détaillant les comportements d'adsorption des gaz purs et des mélanges gazeux, et en mettant en évidence les principales différences et défis à l'aide de points clés et de sections structurées pour plus de clarté.

[action de recherche]

Choisir des citations

D'accord, laisse-moi voir. Je m’appuie sur [3], [20], [22] et [21] pour leurs éclaircissements clairs sur la sorption bimode et les mélanges gazeux.

Cartographier les paramètres

Je rassemble les noms des paramètres pour éviter toute confusion. On conserve (k), (C_H'), et (b) pour plus de clarté. Les équations pour le gaz pur et le mélange sont détaillées et clairement présentées.

Relever les défis

Je m'attaque aux ajustements de paramètres multi-solution, à la plasticisation des polymères et aux effets temporels. Ces subtilités rendent la prédiction de la sorption de gaz purs et mixtes difficile.

Assembler

Je structure des sections sur les différences de sorption, le modèle à double mode pour les gaz purs, son extension aux gaz mélangés, ainsi que les défis associés. Cette progression semble logique et efficace.

Taux de réussite sur des tâches de niveau expert en fonction de la valeur économique estimée
Taux de réussiteValeur économique estimée
Taux de réussite sur des tâches de niveau expert en fonction du nombre d’heures estimé
Taux de réussiteHeures estimé
La valeur économique estimée d’une tâche est davantage corrélée au taux de réussite qu’au nombre d’heures dont un être humain aurait besoin pour l’effectuer. Les tâches jugées difficiles par les modèles ne sont pas celles qui prennent le plus de temps aux êtres humains.

Limitations

Deep research unlocks significant new capabilities, but it’s still early and has limitations. It can sometimes hallucinate facts in responses or make incorrect inferences, though at a notably lower rate than existing ChatGPT models, according to internal evaluations. It may struggle with distinguishing authoritative information from rumors, and currently shows weakness in confidence calibration, often failing to convey uncertainty accurately. At launch, there may be minor formatting errors in reports and citations, and tasks may take longer to kick off. We expect all these issues to quickly improve with more usage and time.

Access

Deep research in ChatGPT is currently very compute intensive. The longer it takes to research a query, the more inference compute is required. We are starting with a version optimized for Pro users today, with up to 100 queries per month. Plus and Team users will get access next, followed by Enterprise. We are still working on bringing access to users in the United Kingdom, Switzerland, and the European Economic Area. 

All paid users will soon get significantly higher rate limits when we release a faster, more cost-effective version of deep research powered by a smaller model that still provides high quality results. 

In the coming weeks and months, we’ll be working on the technical infrastructure, closely monitoring the current release, and conducting even more rigorous testing. This aligns with our principle of iterative deployment. If all safety checks continue to meet our release standards, we anticipate releasing deep research to Plus users in about a month.

Évolutions prévues

La recherche approfondie est disponible dès aujourd’hui sur ChatGPT Web, et sera déployée sur les applis mobiles et de bureau dans le courant du mois. Actuellement, la recherche approfondie peut accéder au Web public et à tous les fichiers téléversés. À l’avenir, vous pourrez connecter des sources de données plus spécialisées — élargissant ainsi son accès à des ressources internes ou sur abonnement — afin de rendre ses sorties encore plus robustes et personnalisés.

À plus long terme, nous envisageons l’intégration d’expériences agentiques dans ChatGPT, capables d’effectuer des recherches et des tâches concrètes de façon asynchrone. La combinaison de la recherche approfondie, qui peut effectuer des investigations en ligne asynchrones, et d’Operator, qui peut agir dans le monde réel, permettra à ChatGPT d’accomplir pour vous des tâches de plus en plus sophistiquées.


Addenda du 3 février 2025 : Nous avons mené des tests de sécurité rigoureux, des évaluations de préparation et des analyses de gouvernance sur la version préliminaire d’o3 qui sous-tend la recherche approfondie, et l’avons classée comme présentant un risque moyen(s'ouvre dans une nouvelle fenêtre). Nous avons également effectué des tests de sécurité supplémentaires afin de mieux comprendre les risques supplémentaires liés à la capacité de la recherche approfondie à naviguer sur le Web, et nous avons ajouté de nouvelles mesures d’atténuation. Nous continuerons à tester et à surveiller de près la version limitée actuelle. Nous partagerons nos conclusions et les mesures de sécurité mises en place pour la recherche approfondie dans une fiche système lorsque nous étendrons l’accès aux utilisateurs Plus.

Footnotes

  1. 1

    We found that the ground-truth answers for this dataset were widely leaked online and have blocked several websites or URLs accordingly to ensure a fair evaluation of the model.

Authors

OpenAI

Research Leads

Isa Fulford, Zhiqing Sun

Foundational Contributors

Alex Tachard Passos, Alexandra Barr, Allison Tam, Charlotte Cole, Hyung Won Chung, Jason Wei, Jon Blackman, Scott Mayer McKinney, Valerie Qi

Core Contributors

Research

Elaine Ya Le, Eric Mitchell, Eric Wallace, Hyung Won Chung, Ignasi Clavera, Leo Liu, Lorenz Kuhn, Louis Feuvrier, Max Schwarzer, Saachi Jain, Scottie Yan, Shunyu Yao, Vitchyr Pong

Deployment

Carpus Chang, Harry Zhao, Joseph Trasatti, Joshua Dickens, Matt Kaufer, Mike Trpcic, Minnia Feng, Neel Ajjarapu, Peter Vidani,  Sean Fitzgerald

Contributors

Research

Ahmed El-Kishky, AJ Ostrow, Alexander Wei, Andrei Gheorghe, Andrew Kondrich, Andrey Mishchenko, Anuj Nair, Behrooz Ghorbani, Brydon Eastman, Chak Li, Foivos Tsimpourlas, Francis Song, Giambattista Parascandolo,Gildas Chabot, Hessam Bagherinezhad, Haitang Hu, Hongyu Ren, Henry Aspegren, Hunter Lightman, Ilya Kostrikov, Ilge Akkaya, James Lennon, Jean Harb, Jonathan Ward, Kai Chen, Katy Shi, Kevin Liu, Kevin Yu, Manuka Stratta, Marvin Zhang, Mengyuan Yan,  Mostafa Rohaninejad, Noam Brown, Phoebe Thacker, Raz Goan, Reah Miyara, Spencer Papay, Taylor Gordon, Wenda Zhou, Wenlei Xie, Yash Patil, Yann Dubois, Youlong Cheng, Yushi Wang, Wyatt Thompson

+ all the contributors to o3.

Safety Systems

Adam Kalai, Alex Beutel, Andrea Vallone, Andy Applebaum, David Robinson, Elizabeth Proehl, Evan Mays, Grace Zhao, Irina Kofman, Jason Phang, Joaquin Quinonero Candela, Joel Parish, Kevin Liu, Kristen Ying, Lama Ahmad, Leon Maksin, Leyton Ho, Meghan Shah, Michele Wang, Miles Wang, Phillip Guo, Olivia Watkins, Owen Campbell-Moore, Patrick Chao, Sam Toizer, Samuel Miserendino, Sandhini Agarwal, Tejal Patwardhan, Tina Sriskandarajah, Troy Peterson, Yaodong Yu, Yunyun Wang

Deployment

Adam Koppel, Adam Wells, Adele Li, Andy Applebaum, Andrey Malevich, Andrew Duberstein, Andrew Howell, Anton Tananaev, Ashley Tyra, Brandon Walkin, Bryan Ashley, Cary Bassin, Cary Hudson, Cory Decareaux, Cristina Scheau, Derek Chen, Dibya Bhattacharjee, Drea Lopez, Eric Antonow, Eric Burke, Filippo Raso, Fotis Chantzis, Freddie Sulit, Harris Cohen, Heather Whitney, Jay Dixit, Jeffrey Han, Jen Robinson, Jessica Shieh, Joel Parish, Kan Wu, Kevin Gladstone, Kshitij Wadhwa, Leo Vandriel, Leyton Ho, Liang Chen, Madeline Christian, Mamie Rheingold, Matt Jones, Michelle Fradin, Mike McClay, Mingxuan Wang, Nacho Soto, Niko Felix, Patrick Delaney, Paul McMillan, Philip Pronin, Rodrigo Riaza Perez, Samuel Miserendino, Scott Ethersmith, Steven Baldwin, Thomas Dimson, Tomo Hiratsuka, Yaming Lin, Yara Khakbaz, Yining Chen

Leadership

Akshay Nathan, Greg Brockman, Hannah Wong, Jakub Pachocki, Jerry Tworek, Johannes Heidecke, Josh Tobin, Liam Fedus, Mark Chen, Mia Glaese, Nick Turley, Sam Altman, Wojciech Zaremba