تخطي إلى المحتوى الرئيسي
OpenAI

16 أبريل 2025

إصدارالمنتج

Introducing OpenAI o3 and o4-mini

جاري التحميل...

تحديث في 10 يونيو 2025: أصبح OpenAI o3‑pro متاحًا الآن لمستخدمي Pro في ChatGPT، وكذلك في واجهة برمجة التطبيقات (API) الخاصة بنا. مثل OpenAI o1‑pro، يُعدّ o3‑pro إصدارًا من نماذجنا الأكثر ذكاءً، صُمم نموذج OpenAI o3 للتفكير لفترة أطول وتقديم إجابات موثوق بها للغاية. يمكن العثور على التفاصيل الكاملة في ملاحظات الإصدار(يفتح في نافذة جديدة).


اليوم نطلق OpenAI o3 و o4-mini، أحدث نماذجنا من سلسلة o التي تم تدريبها للتفكير لفترات أطول قبل تقديم الإجابات. من بين جميع النماذج التي أصدرناها حتى الآن، تُعد هذه الأكثر ذكاءً، وتمثل تحولًا كبيرًا في قدرات ChatGPT للجميع بدءًا من المستخدم الفضولي وصولًا إلى الباحثين المتقدمين. ولأول مرة، يمكن لنماذج الاستدلال لدينا أن تستخدم وتدمج أدوات ChatGPT بشكل وكيل Agentic—بما في ذلك البحث على الويب، وتحليل الملفات والبيانات المرفوعة باستخدام Python، والاستدلال العميق على المدخلات البصرية، وحتى توليد الصور. الأهم من ذلك، تم تدريب هذه النماذج على الاستدلال حول متى وكيف تستخدم الأدوات، لتقديم إجابات مفصلة ومدروسة بالتنسيق الصحيح، غالبًا في أقل من دقيقة، حتى مع المشكلات والمسائل المعقدة. هذا يتيح لها معالجة الأسئلة متعددة الأوجه بشكل أكثر فعالية، ما يُعد خطوة نحو ChatGPT أكثر ذكاءً قادر على تنفيذ المهام نيابة عنك بشكل مستقل. الجمع بين الاستدلال المتطور والوصول الكامل إلى الأدوات يوفر أداءً أقوى بكثير في معايير أكاديمية ومهام واقعية، ما يضع معيارًا جديدًا في الذكاء وقابلية الاستخدام.

التغييرات

OpenAI o3 هو أقوى نموذج استدلال لدينا يدفع حدود الأداء في البرمجة، والرياضيات، والعلوم، والإدراك البصري، وأكثر من ذلك. يحقق النموذج مستويات قياسية جديدة على المعايير بما في ذلك Codeforces، و SWE-bench (دون الحاجة لإعداد هيكل مخصص للنموذج)، و MMMU، ما يجعله مثاليًا للاستفسارات المعقدة التي تتطلب تحليلاً متعدد الجوانب والتي قد لا تكون إجاباتها واضحة على الفور. يتفوق النموذج بشكل خاص في المهام البصرية مثل تحليل الصور، والمخططات، والرسومات. وأظهرت تقييمات الخبراء الخارجيين أن النموذج OpenAI o3 يرتكب أخطاء رئيسية أقل بنسبة 20 بالمائة مقارنةً بنموذج OpenAI o1 في المهام الواقعية الصعبة—مع تميز واضح في مجالات مثل البرمجة، والأعمال أو الاستشارات، والأفكار الإبداعية. وأشار المختبرون الأوائل إلى دقته التحليلية كشريك فكري موثوق به، وأكدوا على قدرته على إنشاء وتقييم فرضيات جديدة بشكل نقدي—خصوصًا في سياقات علم الأحياء، والرياضيات، والهندسة.

OpenAI o4-mini هو نموذج أصغر حجمًا، مُصمم لتعزيز الاستدلال الفعّال من حيث التكلفة،—يحقق أداءً ملحوظًا بالنسبة لحجمه وتكلفته، لا سيما في الرياضيات، والبرمجة، والمهام البصرية. يُعدّ هذا النموذج الأفضل أداءً في اختبارات AIME لعامي 2024 و2025. على الرغم من أن استخدام جهاز كمبيوتر يقلل بشكل ملحوظ من صعوبة اختبار AIME، إلا إنه من اللافت أن نموذج OpenAI o4-mini يحقق نسبة نجاح 99.5٪ عند المحاولة الأولى (pass@1) و100٪ بالإجماع عند المحاولة الثامنة (consensus@8) في اختبار AIME 2025 عند تمكينه من الوصول إلى مفسّر Python. ورغم أن هذه النتائج ينبغي عدم مقارنتها بأداء النماذج التي لا تتاح لها أدوات، إلا إنها تمثل مثالًا على مدى فاعلية نموذج o4-mini في الاستفادة من الأدوات المتاحة. كما يُظهر نموذج o3 تحسينات مماثلة في AIME 2025 نتيجة لاستخدام الأدوات، محققًا نسبة نجاح 98.4٪ عند المحاولة الأولى (pass@1) وإجماعًا بنسبة 100٪ عند المحاولة الثامنة (consensus@8).

في تقييمات الخبراء، يتفوق نموذج o4-mini أيضًا على سابقه، o3‑mini، في المهام غير المتعلقة بمجالات العلوم والتكنولوجيا والهندسة والرياضيات (STEM) وكذلك في مجالات مثل علم البيانات. وبفضل كفاءته، يدعم o4-mini حدود استخدام أعلى بكثير مقارنةً بنموذج o3، ما يجعله خيارًا قويًا عالي السعة وعالي الإنتاجية للأسئلة التي تستفيد من الاستدلال. وقد صنف الخبراء الخارجيون كلا النموذجين على أنهما يُظهران تحسنًا في اتباع التعليمات وتقديم استجابات أكثر فائدة وقابلة للتحقق مقارنةً بالإصدارات السابقة، وذلك بفضل الذكاء المحسّن ودمج مصادر الويب. وبالمقارنة مع الإصدارات السابقة من نماذج الاستدلال لدينا، يبدو هذان النموذجان أكثر طبيعية وحوارية، لا سيما عند الرجوع إلى الذاكرة والمحادثات السابقة لجعل الاستجابات أكثر تخصيصًا وملاءمة.

القدرات متعدّدة الوسائط

البرمجة

تُجرى جميع اختبارات التقييم الخاصة بـ SWE-bench باستخدام مجموعة ثابتة تتألف من 477 (n) مهمة مُتحقَّق منها، تم اعتمادها والتحقق من صحتها على البنية التحتية الداخلية لدينا.

اتباع التعليمات واستخدام الأدوات بذكاء ذاتي

تُقيَّم جميع النماذج باستخدام إعدادات "جهد استدلال" مرتفعة— والمشابهة لنسخ مثل "o4-mini-high" في ChatGPT.

Continuing to scale reinforcement learning

Throughout the development of OpenAI o3, we’ve observed that large-scale reinforcement learning exhibits the same “more compute = better performance” trend observed in GPT‑series pretraining. By retracing the scaling path—this time in RL—we’ve pushed an additional order of magnitude in both training compute and inference-time reasoning, yet still see clear performance gains, validating that the models’ performance continues to improve the more they’re allowed to think. At equal latency and cost with OpenAI o1, o3 delivers higher performance in ChatGPT—and we've validated that if we let it think longer, its performance keeps climbing.

We also trained both models to use tools through reinforcement learning—teaching them not just how to use tools, but to reason about when to use them. Their ability to deploy tools based on desired outcomes makes them more capable in open-ended situations—particularly those involving visual reasoning and multi-step workflows. This improvement is reflected both in academic benchmarks and real-world tasks, as reported by early testers.

التفكير باستخدام الصور

ChatGPT thinking with images

لأول مرة، يمكن لهذه النماذج دمج الصور مباشرةً في تسلسل استدلالها. فهي لا تكتفي بمشاهدة الصورة—بل تفكر بها. يفتح هذا فئة جديدة من حل المشكلات التي تجمع بين الاستدلال البصري والنصي، وينعكس ذلك في أدائها المتقدم عبر معايير متعددة الوسائط.

يمكن للأشخاص تحميل صورة لسبورة بيضاء، أو مخطط من كتاب دراسي، أو رسم يدوي، ويمكن للنموذج تفسيرها—حتى لو كانت الصورة ضبابية، أو معكوسة، أو منخفضة الجودة. باستخدام الأدوات، يمكن للنماذج التلاعب بالصور فورًا—تدويرها، أو تكبيرها، أو تحويلها كجزء من عملية استدلالها.

تقدم هذه النماذج دقة رائدة في مهام الإدراك البصري، ما يمكّنها من حل الأسئلة التي لم تكن ممكنة سابقًا. يمكنكم الاطّلاع على مدونة أبحاث الاستدلال البصري لمعرفة المزيد.

للاستخدام الاستراتيجي للأدوات

يتمتع النموذجان OpenAI o3 و OpenAI o4-mini بإمكانية الوصول الكامل إلى الأدوات داخل ChatGPT، بالإضافة إلى أدواتك المخصصة من خلال استدعاء الوظائف في واجهة برمجة التطبيقات. تم تدريب هذه النماذج على استخدام الاستدلال في كيفية حل المشكلات، مع القدرة على تحديد الوقت والطريقة الأمثل لاستخدام الأدوات لتقديم إجابات مفصلة ومدروسة بالصياغة الصحيحة بسرعة—عادةً في أقل من دقيقة.

على سبيل المثال، قد يسأل المستخدم: "كيف سيُقارَن استهلاك الطاقة في الصيف في كاليفورنيا بالعام الماضي؟" يمكن للنموذج البحث على الإنترنت عن بيانات المرافق العامة، وكتابة كود Python لبناء توقع، وإنشاء رسم بياني أو صورة، وشرح العوامل الرئيسية وراء التوقُّع، من خلال ربط عدة استدعاءات للأدوات معًا. يُتيح الاستدلال للنماذج التفاعل والتكيف حسب المعلومات التي تواجهها؛ فعلى سبيل المثال، يمكنه البحث على الإنترنت عدة مرات بمساعدة مزوّدي البحث، ومراجعة النتائج، وتجربة عمليات بحث جديدة إذا احتاج إلى مزيد من المعلومات.

يُتيح هذا النهج الاستراتيجي المرن للنماذج معالجة المهام التي تتطلب الوصول إلى معلومات محدثة تتجاوز المعرفة المدمجة في النموذج، بالإضافة إلى القدرة على الاستدلال الموسع، والتركيب، وإنشاء النتيجة عبر الوسائط.

تم إكمال جميع الأمثلة باستخدام OpenAI o3.

OpenAI o3

Solve the following very hard math problem using your in-built knowledge of the literature:

Construct a degree 19 polynomial \ (p(x)) \ in \ mathbb{C}[x] such that \ (X := \ {\, p(x) = p(y) \, \} \ subset \ mathbb{P}^{1} \ times \ mathbb{P}^{1}\ ) has at least 3 (but not all linear) irreducible components over \ mathbb{C}. Choose \ (p(x)\ ) to be odd, monic, have real coefficients and linear coefficient \ (-19\ ) and calculate \ (p(19)\ ).

تم استخدام الاستدلال في بناء كثيرات الحدود لمدة 55 ثانية
  • The curve defined by p(x) = p(y) factors if p(x) is decomposable or has repeated factors. Actually, p(x)-p(y) always factors, and it’s divisible by (x-y). This gives one factor, and the rest is a degree d-1 polynomial in x and y. For the curve to have at least three irreducible components, p(x)-p(y) must factor into at least three nontrivial factors. Each factor corresponds to a component in projective space, and at least one must be nonlinear.
  • I’m checking the Dickson polynomials D_n(x,a) and focusing on their coefficients. With a=1, it seems the leading coefficient is always 1, confirming that Dickson polynomials are monic. The linear coefficient for odd n is following a predictable sign pattern: for n=19, it gives a coefficient of -19, which is exactly what I need. So the Dickson polynomial D_n(x,1) with odd n fits nicely with the linear coefficient I was looking for.
  • I've confirmed that the linear coefficient for p(x)=D19(x)p(x) = D_{19}(x)p(x)=D19​(x) is correct, with the necessary scaling factor to match. Now for the next step, I need to compute D19(19)D_{19}(19)D19​(19). Since Tn(z)T_n(z)Tn​(z) grows quickly for real z>1z > 1z>1, I plan to compute this value using Python, leveraging the recurrence to avoid mistakes—it's going to be a big number. I'll make sure to present the numeric result neatly so it's understandable since the coefficients are integers.
  • The Dickson polynomial D_{19}(x,1) is confirmed to have the required properties: monic, odd, real coefficients, and a linear coefficient of -19. The factorization of D_{19}(x) into irreducible components is also verified and satisfies the condition of having at least 10 components (1 linear + 9 quadratics). To compute p(19), we'll use the recurrence relation for Dickson polynomials, but there's also a closed-form expression involving cosine that could be handy here. I'll proceed accordingly!
  • I confirmed the linear coefficient is working correctly, which means now I need to calculate p(19)=D19(19)p(19) = D_{19}(19)p(19)=D19​(19). This involves evaluating T19(9.5)T_{19}(9.5)T19​(9.5), which grows rapidly. To ensure I get an accurate result, I'll compute this using recurrence in Python. The result is a large number: 1,876,572,071,974,094,803,391,179. I'll use the commas to make it easier to read: p(19)=1,876,572,071,974,094,803,391,179p(19) = 1,876,572,071,974,094,803,391,179p(19)=1,876,572,071,974,094,803,391,179.
  • For a = 1, there’s a relationship between Dickson polynomials and Chebyshev polynomials: D_n(x, 1) = 2^(n-1) T_n(x/2). Checking this, we see that the definition of D_n(u + 1/u) aligns well with Chebyshev’s formula. By setting x = 2 cos(θ), we find that D_n(x) equals 2 T_n(x/2). Importantly, the leading coefficient works out to 1, confirming the identity holds. This is nice!
  • Now, I need to verify that p(x)−p(y)p(x) - p(y)p(x)−p(y) factors as desired, relying on the known Dickson polynomial factorization. According to the literature (like Fried and Jarden), the difference Dn(x)−Dn(y)D_n(x) - D_n(y)Dn​(x)−Dn​(y) factors into a product involving (x−y)(x - y)(x−y) and other expressions. I'll provide the explicit polynomial D19(x,1)D_{19}(x, 1)D19​(x,1), list the coefficients, and explain how it satisfies the desired properties: monic, odd, etc. Lastly, I'll compute p(19)p(19)p(19).

Analyzed

Python

1
from math import comb, cos, acos
2
# Let's compute Dickson D_n(x,a=1) recursively
3
def dickson(n,x,a=1):
4
if n==0:
5
return 2
6
if n==1:
7
return x
8
Dm2=2
9
Dm1=x
10
for k in range(2,n+1):
11
D= x*Dm1 - a*Dm2
12
Dm2, Dm1 = Dm1, D
13
return Dm1
14

15
d19 = dickson(19,19,1)
16
d19

1876572071974094803391179

Analyzed

Python

1
d19

1876572071974094803391179

Analyzed

Python

1
import locale, sys, math, json, textwrap, re, decimal

Analyzed

Python

1
"{:,}".format(d19)

'1,876,572,071,974,094,803,391,179'

Analyzed

Python

1
# compute coefficients of Dickson polynomial D_n(x,1) via recurrence polynomial representation
2
from sympy import symbols, Poly
3

4
x = symbols('x')
5
def dickson_poly(n):

إنشاء كثير حدود على الشكل التالي: (x**19 - 19*x**17 + 152*x**15 - 665*x**13 + 1729*x**11 - 2717*x**9 + 2508*x**7 - 1254*x**5 + 285*x**3 - 19*x, x,

Analyzed

Python

1
poly19.as_expr()

x**19 - 19*x**17 + 152*x**15 - 665*x**13 + 1729*x**11 - 2717*x**9 + 2508*x**7 - 1254*x**5 + 285*x**3 - 19*x

Done

A convenient way to force many factors in
p(x)    p(y)p(x) \;-\; p(y) is to use a Dickson polynomial of the first kind.
For a parameter
aCa \in \mathbb{C} in math these are defined by

D0 ⁣(x,a)=2,  D1 ⁣(x,a)=x,  Dn ⁣(x,a)=xDn1 ⁣(x,a)aDn2 ⁣(x,a)(n2),D_0\!\left(x,\, a\right) = 2,\; D_1\!\left(x,\, a\right) = x,\; D_n\!\left(x,\, a\right) = x\,D_{n-1}\!\left(x,\, a\right) - a\,D_{n-2}\!\left(x,\, a\right)\quad (n \ge 2),

and satisfy the functional identity

Dn ⁣(u+au,a)=un+anun.D_n\!\left(u + \frac{a}{u},\, a\right) = u^{n} + \frac{a^{n}}{u^{n}}.


1. Choosing the polynomial

Take a=1a = 1 and n=19n=19.
Because
nn is odd, D19 ⁣(x,1)D_{19}\!\left(x,\, 1\right) is an odd polynomial; the recurrence immediately shows it is monic and has integer (hence real) coefficients.
The coefficient of
xx is x=(1)n12n=19,x = (-1)^{\frac{n-1}{2}}\,n = -19, so all requested normalisations are satisfied.

Writing it out gives

p(x)=D19 ⁣(x,1)=x1919x17+152x15665x13+1729x112717x9+2508x71254x5+285x319x. \boxed{% p(x) = D_{19}\!\left(x,1\right) = x^{19} - 19x^{17} + 152x^{15} - 665x^{13} + 1729x^{11} - 2717x^{9} + 2508x^{7} - 1254x^{5} + 285x^{3} - 19x% }\,.


2. Irreducible components of fX  =  {p(x)=p(y)}fX \;=\; \bigl\{\, p(x) = p(y) \,\bigr\}

For Dickson polynomials one has the classical factorisation

Dn ⁣(x,1)    Dn ⁣(y,1)  =  (xy)j=1n12(x2+y22cos ⁣(2πjn)xy4sin2 ⁣(πjn)),D_n\!\left(x,1\right) \;-\; D_n\!\left(y,1\right) \;=\; (x - y)\, \prod_{j=1}^{\frac{n-1}{2}} \Bigl( x^{2} + y^{2} - 2\cos\!\bigl(\tfrac{2\pi j}{n}\bigr)\,xy - 4\sin^{2}\!\bigl(\tfrac{\pi j}{n}\bigr) \Bigr),

where each quadratic factor is irreducible over C\mathbb{C} (see, e.g., Lidl–Niederreiter, Finite Fields, §3.6).
For
n=19n=19 this gives

  • one linear component x=y;x=y;
  • nine quadratic components (corresponding to (j=1,,9).\bigl(j = 1,\,\ldots,\,9\bigr).

Hence XP1×P1X \subset \mathbb{P}^{1} \times \mathbb{P}^{1} has 1010 irreducible components, at least three of them and not all linear, as required.


3. Evaluating p(19)p(19)

Using the recurrence (or the identity Dn ⁣(x,1)  =  2Tn ⁣(x2)D_n\!\left(x,\,1\right) \;=\; 2\,T_n\!\bigl(\tfrac{x}{2}\bigr) with Chebyshev TnT_n one obtains

p(19)  =  D19 ⁣(19,1)  =  1876572071974094803391179.p(19) \;=\; D_{19}\!\left(19,\,1\right) \;=\; 1\,876\,572\,071\,974\,094\,803\,391\,179.


Thus the polynomial above fulfils every condition, and

p(19)  =  1,876,572,071,974,094,803,391,179.\boxed{% p(19) \;=\; 1{,}876{,}572{,}071{,}974{,}094{,}803{,}391{,}179 }.

OpenAI o1

Solve the following very hard math problem using your in-built knowledge of the literature:

Construct a degree 19 polynomial \ (p(x)) \ in \ mathbb{C}[x] such that \ (X := \ {\, p(x) = p(y) \, \} \ subset \ mathbb{P}^{1} \ times \ mathbb{P}^{1}\ ) has at least 3 (but not all linear) irreducible components over \ mathbb{C}. Choose \ (p(x)\ ) to be odd, monic, have real coefficients and linear coefficient \ (-19\ ) and calculate \ (p(19)\ ).

تم التفكير لمدة دقيقة واحدة و19 ثانية

I’m piecing together a degree 19 polynomial with only odd powers and a linear coefficient of -19, like: p(x)=x19+a17x17+…+a1xp(x) = x^{19} + a_{17}x^{17} + \ldots + a_1xp(x)=x19+a17​x17+…+a1​x.

I'm examining if the polynomial p(x)=x19+a17x17+…+a3x3−19xp(x) = x^{19} + a_{17}x^{17} + \ldots + a_3x^3 - 19xp(x)=x19+a17​x17+…+a3​x3−19x has a notable classical form, considering symmetry or factorization for multiple irreducible components.

To ensure p(x)p(x)p(x) has three or more irreducible components, I’m considering the factorization of p(x)−p(y)p(x) - p(y)p(x)−p(y) into at least three irreducible factors in C[x,y]\mathbb{C}[x,y]C[x,y].

I'm working through x19−y19x^{19} - y^{19}x19−y19 to ensure it balances linear and nonlinear factors, aiming for a polynomial with at least three irreducible components that aren't all linear.

Taking a closer look at how p(x)−p(y)p(x) - p(y)p(x)−p(y) can be factored into three distinct polynomials in xxx, aiming to achieve the desired irreducible components.

I'm thinking about how composing ppp with simpler polynomials, like xm−cx^m - cxm−c, could result in multiple irreducible components, achieving at least three distinct factors.

I’m exploring the factorization of p(x)−p(y)p(x) - p(y)p(x)−p(y) with cyclotomic polynomials. This method generates nnn linear irreducible factors, which might not achieve the required three distinct components.

I'm focusing on constructing an "odd" and monic polynomial, ensuring all exponents are odd and the leading term is x19x^{19}x19. This approach aims to achieve the desired factorization.

I'm working with the Chebyshev polynomials to ensure p(x)−p(y)p(x) - p(y)p(x)−p(y) has at least three irreducible components, leveraging their even or odd properties to manage coefficients.

Considering the odd Chebyshev polynomial T19(x)T_{19}(x)T19​(x) for potential factorization, while also examining composite polynomials of lower degrees to enhance factorization properties.

I'm analyzing how a polynomial composed of lower-degree polynomials, like (x3−3x)k(x^3 - 3x)^k(x3−3x)k, could yield p(x)−p(y)p(x) - p(y)p(x)−p(y) with at least three irreducible components.

Piecing together polynomials with integer coefficients, like (x3−3x)k(x^3 - 3x)^k(x3−3x)k, to achieve factorization in p(x)−p(y)p(x) - p(y)p(x)−p(y) with at least three irreducible components, aiming for degree 19.

I’m examining how p(x)=(x3−3x)kp(x) = (x^3 - 3x)^kp(x)=(x3−3x)k or p(x)=x19−19xp(x) = x^19 - 19xp(x)=x19−19x might yield p(x)−p(y)p(x) - p(y)p(x)−p(y) with three irreducible components, focusing on ensuring the polynomial is of degree 19.

I’m analyzing p(x)−p(y)p(x) - p(y)p(x)−p(y) into (x−y)(x18+x17y+…+y18−19)(x-y)(x^{18} + x^{17}y + \ldots + y^{18} - 19)(x−y)(x18+x17y+…+y18−19) to identify irreducible components. The polynomial factor x18+x17y+…+y18−19x^{18} + x^{17}y + \ldots + y^{18} - 19x18+x17y+…+y18−19 remains challenging to factor further.

I’m thinking through a new approach: adjusting the Chebyshev polynomial T19(x)T_{19}(x)T19​(x) to make it monic, aiming to achieve at least three irreducible components in p(x)−p(y)p(x) - p(y)p(x)−p(y).

OK, let's think through. I’m tweaking T19(x)T_{19}(x)T19​(x)'s coefficients to keep the polynomial monic and check if it simplifies into multiple irreducible components.

I'm thinking over various factorization strategies for a monic polynomial of degree 19. The goal is to ensure at least one non-linear factor and achieve at least three irreducible components in p(x)−p(y)p(x) - p(y)p(x)−p(y).

I’m updating my approach to factor x2+xy+y2−1x^2 + xy + y^2 - 1x2+xy+y2−1 over complex numbers by exploring change of variables and third roots of unity. This helps in achieving the desired polynomial structure.

I'm combining x3−xx^3 - xx3−x with x19−19xx^{19} - 19xx19−19x to tweak the polynomial's coefficients and complexity, aiming to include more non-linear factors for the desired irreducibility.

Piecing together p(x)=x19−x3−19xp(x) = x^{19} - x^3 - 19xp(x)=x19−x3−19x to ensure it’s odd, monic, and has the required linear coefficient. This targets the desired irreducible factorizations.

I’m mapping out the second factor x18+…+y18−x2−xy−y2−19x^{18} + \ldots + y^{18} - x^2 - xy - y^2 - 19x18+…+y18−x2−xy−y2−19 to see if it can split into three irreducible components.

I’m considering methods to factorize the polynomial by making it divisible by x−yx - yx−y and ensuring the remaining factor splits into exactly two irreducible components, aiming for a less complex factorization.

I’m examining the polynomial x18+x17y+…+y18x^{18} + x^{17}y + \ldots + y^{18}x18+x17y+…+y18 and noting it simplifies to x19−y19x−y\frac{x^{19} - y^{19}}{x - y}x−yx19−y19​, which might reveal further irreducible factors.

I’m mapping out the polynomial x(x18−1)−y(y18−1)x−y\frac{x(x^{18}-1) - y(y^{18}-1)}{x-y}x−yx(x18−1)−y(y18−1)​ for further factorization. This might yield just two irreducible components, which falls short of three.

I’m exploring whether the polynomial p(x)=x19−(x3)p(x) = x^19 - (x^3)p(x)=x19−(x3) can be expressed as the composition of a smaller polynomial with xkx^kxk, potentially revealing multiple irreducible components.

I'm examining if the polynomial T19(x)T_{19}(x)T19​(x) can be factored using trigonometric identities, seeking partial factorization without fully linearizing, to gain multiple irreducible components.

OK, let me see. Trigonometric identities show multiple solutions for θ\thetaθ and ϕ\phiϕ, likely leading to 19 or 38 linear factors for T19(x)T_{19}(x)T19​(x).

I’m examining how the equation arccos⁡x=±arccos⁡y+2kπ19\arccos x = \pm \arccos y + \frac{2k\pi}{19}arccosx=±arccosy+192kπ​ leads to possible multiple branches, potentially irreducible in the algebraic sense, and needing an example with at least three non-linear irreducible components.

OK, let me see. I’m pulling together details on the polynomial x3(x2−1)8+xx^3 (x^2 - 1)^8 + xx3(x2−1)8+x. It’s monic, with x19x^{19}x19 as the leading term, ensuring it meets key criteria.

I’m noting that the polynomial p(x)=x3(x2−1)8+xp(x) = x^3 (x^2 - 1)^8 + xp(x)=x3(x2−1)8+x is odd, with its linear coefficient patterning to -19.

I’m figuring out how to adjust the linear coefficient of polynomial p(x)p(x)p(x) to -19 by adding a constant factor ccc in front of xxx to ensure it’s adequately modified.

By tweaking the linear coefficient of p(x)=x3(x2−1)8+cxp(x) = x^3 (x^2 - 1)^8 + c xp(x)=x3(x2−1)8+cx to -19, it ensures the polynomial remains monic, odd, and real.

I’m working on adding a constant factor ccc to xxx in p(x)=x3(x2−1)8+cxp(x) = x^3 (x^2 - 1)^8 + c xp(x)=x3(x2−1)8+cx to ensure the linear coefficient is -19, making the polynomial monic, odd, and real.

I'm piecing together the polynomial p(x)=x3(x−1)8(x+1)8p(x) = x^3 (x-1)^8 (x+1)^8p(x)=x3(x−1)8(x+1)8 and considering how p(x)−p(y)p(x) - p(y)p(x)−p(y) might factor with factors like x−yx-yx−y.

I’m confirming p(x)p(x)p(x) is monic, odd, and real, with a linear coefficient of -19, by expanding x3(x2−1)8x^3 (x^2 -1)^8x3(x2−1)8 to set the constant ccc.

I found that for p(x) to have a coefficient of -19 for the x term, c must be -19. The polynomial, p(x), incorporates this constant and preserves the original polynomial's structure.

Below is one concrete example (over the reals) of an odd, monic, degree 19 polynomial with linear coefficient 19-19 whose zero-locus relation {p(x)=p(y)} in P1×P1\{\,p(x)=p(y)\,\}\ \text{in }\mathbb{P}^{1}\times\mathbb{P}^{1} splits into at least three irreducible components (and not all components are linear). We then compute p(19)p(19).


1. The polynomial

Consider

p(x)  =  x3(x21)8    19x.p(x) \;=\; x^{3}\,\bigl(x^{2}-1\bigr)^{8} \;-\; 19x.

We can expand

x3(x21)8  =  x19    8x17  +  28x15    56x13  +  70x11    56x9  +  28x7    8x5  +  x3.x^{3}\,\bigl(x^{2}-1\bigr)^{8} \;=\; x^{19}\;-\;8x^{17}\;+\;28x^{15}\;-\;56x^{13}\;+\;70x^{11} \;-\;56x^{9}\;+\;28x^{7}\;-\;8x^{5}\;+\;x^{3}.

Hence

p(x)  =  x19    8x17  +  28x15    56x13  +  70x11    56x9  +  28x7    8x5  +  x3    19x.p(x) \;=\; x^{19} \;-\; 8x^{17} \;+\; 28x^{15} \;-\; 56x^{13} \;+\; 70x^{11} \;-\; 56x^{9} \;+\; 28x^{7} \;-\; 8x^{5} \;+\; x^{3} \;-\; 19x.

Checking the required properties

Degree 19, monic:
The leading term is
x19x^{19}with coefficient 11.

Odd polynomial:
All exponents are odd
(19,17,,3,1),\bigl(19,\,17,\,\ldots,\,3,\,1\bigr), and the constant term is 00. Indeed,

p(x)  =  p(x),p(-x) \;=\; -\,p(x),

which makes pp an odd polynomial.

Real coefficients:
All coefficients are real integers.

Linear coefficient 19-19:
The coefficient of
xx is clearly 19-19.

At least three irreducible components, not all linear:
Over
C\mathbb{C}, the locus

X  =  {(x,y):p(x)=p(y)}    P1×P1X \;=\; \bigl\{\, (x,y) : p(x)=p(y) \,\bigr\} \;\subset\; \mathbb{P}^{1}\times\mathbb{P}^{1}

factors in part because p(x)p(x) has (for instance) the repeated factors (x21)8\bigl(x^{2}-1\bigr)^{8} in the big piece x3(x21)8x^{3}\,\bigl(x^{2}-1\bigr)^{8}. One sees that {p(x)=p(y)}\{\,p(x)=p(y)\,\} contains (at least) the divisor $${x=y\}$$ plus further factors coming from the roots x=0  or  x=±1,x = 0 \;\text{or}\; x = \pm 1, ensuring multiple irreducible components (and not all of them are hyperplanes).


2. Computing p(19)p(19)

A direct substitution x=19x=19 gives a large integer. Symbolic expansion or a computer algebra system yields

p(19)  =  1934999285524070399999639.p(19) \;=\; 1934999285524070399999639.

Hence the required value is

\boxed{\,p(19) \;=\; 1934999285524070399999639\,}. \] ​:contentReference[oaicite:0]{index=0}​

يتمكّن نموذج OpenAI o3 من تقديم الإجابة الصحيحة دون الحاجة إلى استخدام البحث، بينما يفشل نموذج OpenAI o1 في ذلك.

تعزيز الاستدلال الفعّال من حيث التكلفة

التكلفة مقابل الأداء: OpenAI o3‑mini و OpenAI o4-mini
تقييمات AIME للنموذجين OpenAI o3-mini و OpenAI o4-mini
تقييمات GPQA للنموذجين OpenAI o3-mini و OpenAI o4-mini
التكلفة مقابل الأداء: OpenAI o1 و OpenAI o3
تقييمات AIME للنموذجين OpenAI o3 و OpenAI o4
تقييمات GPQA للنموذجين OpenAI o3 و OpenAI o4

يُعدّ نموذجا OpenAI o3 و OpenAI o4-mini أذكى النماذج التي أصدرناها على الإطلاق، وغالبًا ما يكونان أكثر كفاءة من سابقيهما، OpenAI o1 و OpenAI o3‑mini. على سبيل المثال، في مسابقة الرياضيات AIME لعام 2025، يتفوق منحنى "حد التكلفة والأداء" لنموذج OpenAI o3 بشكل واضح على منحنى OpenAI o1، وبالمثل، يتفوق منحنى OpenAI o4-mini بشكل واضح على OpenAI o3‑mini. بشكل عام، نتوقع أنه في معظم الاستخدامات الواقعية، سيكون نموذجا OpenAI o3 و OpenAI o4-mini أذكى وأقل تكلفة من OpenAI o1 و OpenAI o3‑mini على التوالي.

Safety

Each improvement in model capabilities warrants commensurate improvements to safety. For OpenAI o3 and o4-mini, we completely rebuilt our safety training data, adding new refusal prompts in areas such as biological threats (biorisk), malware generation, and jailbreaks. This refreshed data has led o3 and o4-mini to achieve strong performance on our internal refusal benchmarks (e.g., instruction hierarchy, jailbreaks). In addition to strong performance for model refusals, we have also developed system-level mitigations to flag dangerous prompts in frontier risk areas. Similar to our earlier work in image generation, we trained a reasoning LLM monitor which works from human-written and interpretable safety specifications. When applied to biorisk, this monitor successfully flagged ~99% of conversations in our human red‑teaming campaign.

We stress tested both models with our most rigorous safety program to date. In accordance with our updated Preparedness Framework, we evaluated o3 and o4-mini across the three tracked capability areas covered by the Framework: biological and chemical, cybersecurity, and AI self-improvement. Based on the results of these evaluations, we have determined that both o3 and o4‑mini remain below the Framework's "High" threshold in all three categories. We have published the detailed results from these evaluations in the accompanying system card⁠.

Codex CLI: الاستدلال المتقدّم في سطر الأوامر

نشارك أيضًا تجربة جديدة: Codex CLI، وهو وكيل برمجي خفيف الوزن يمكنكم تشغيله مباشرةً من نافذة الأوامر على الأجهزة الطرفية لديكم. يعمل البرنامج محليًا على أجهزة الكمبيوتر الخاصة بكم، وصُمم لتعظيم قدرات الاستدلال في نماذج مثل o3 و o4-mini، مع دعم قادم لنماذج API إضافية مثل نموذج GPT‑4.1.

يمكنكم الاستفادة من الاستدلال متعدد الوسائط مباشرةً من سطر الأوامر عن طريق تمرير لقطات شاشة أو الرسوم التخطيطية منخفضة الدقة إلى النموذج، مع إمكانية الوصول إلى الكود محليًا. تُعدّ هذه واجهة بسيطة لربط نماذجنا بالمستخدمين وأجهزة الكمبيوتر الخاصة بهم. Codex CLI متاح بالكامل كمصدر مفتوح اليوم على github.com/openai/codex(يفتح في نافذة جديدة) .

إلى جانب ذلك، نحن بصدد إطلاق مبادرة بقيمة مليون دولار لدعم المشاريع التي تستخدم واجهة الأوامر Codex CLI ونماذج OpenAI. سنقوم بتقييم وقبول تطبيقات المنح بمبالغ قدرها 25,000 دولار أمريكي على شكل أرصدة API. يمكن إرسال المقترحات من هنا.

إمكانية الوصول

سيتمكن مستخدمو ChatGPT Plus وPro وTeam من الوصول إلى النماذج o3 و o4-mini و o4-mini-high في محدد النماذج اعتبارًا من اليوم، لتحل محل النماذج o1 و o3‑mini و o3‑mini‑high. وسيحصل مستخدمو ChatGPT Enterprise وEdu على إمكانية الوصول خلال أسبوع واحد. يمكن للمستخدمين الحسابات المجانية Free تجربة o4-mini عن طريق اختيار "فكر" في واجهة الكتابة قبل إرسال استفسارهم. تظل حدود المعدلات لجميع الخطط كما هي دون تغيير مقارنةً بمجموعة النماذج السابقة.

نتوقع أن نصدر OpenAI o3‑pro خلال الأسابيع القليلة القادمة مع دعم كامل للأدوات. وفي الوقت الحالي، لا يزال بإمكان مستخدمي Pro الوصول إلى o1‑pro.

كلا النموذجين o3 و o4-mini متاحان اليوم أيضًا للمطورين عبر Chat Completions API (واجهة برمجة تطبيقات إكمال الدردشة) وResponses API (واجهة برمجة تطبيقات الاستجابات) (قد يحتاج بعض المطورين إلى التحقق من مؤسساتهم(يفتح في نافذة جديدة) للوصول إلى هذه النماذج). تدعم Responses API ملخصات الاستدلال، والقدرة على الاحتفاظ بالرموز المميزة حول استدعاءات الوظائف لتحسين الأداء، وستدعم قريبًا أدوات مدمجة مثل البحث على الويب، والبحث عن الملفات، ومنفّذ التعليمات البرمجية ضمن استدلال النموذج. لبدء الاستخدام، يمكنكم استكشاف مستنداتنا(يفتح في نافذة جديدة) ومتابعة التحديثات القادمة.

What's next

Today's updates reflect the direction our models are heading in: we’re converging the specialized reasoning capabilities of the o-series with more of the natural conversational abilities and tool use of the GPT‑series. By unifying these strengths, our future models will support seamless, natural conversations alongside proactive tool use and advanced problem-solving.


Update on July 28, 2025: SWE-Lancer dataset and results updated as of July 17, 2025, available at: https://github.com/openai/preparedness(يفتح في نافذة جديدة) and in our system cards. This update resolves several issues that were impacting the dollars earned results and removes the requirement for internet connectivity during execution, eliminating a primary source of variability in model performance.

Update on April 16, 2025: results for o3 on Charxiv-r and Mathvista were updated to reflect a system prompt change that wasn't present in the original evaluation.

إعادة تشغيل البث المباشر

المؤلف

OpenAI

الهوامش

* يتم احتساب متوسط أرقام تقييم tau-bench في 5 جولات تشغيل لتقليل التباين، وتم تنفيذها دون أيّ أدوات أو مطالبات مخصصة. ووجدنا أن عمليات الطرح التجاري لـ tau-bench أكثر عرضة لأخطاء نماذج المستخدمين. أما الأرقام الخاصة بالشريط المظلّل، فتم تشغيلها باستخدام GPT-4.1 كنموذج مستخدم، لأنه يتفوق بشكل كبير على GPT-4o في اتباع التعليمات.

* يستخدم المعيار SWE-bench حدًا أقصى لطول السياق يبلغ 256 ألف رمز مميز، ما يحسن معدل حل المشكلات لنموذج OpenAI o4-mini بحوالي 3٪ ويؤثر على معدل حل نموذج OpenAI o3 بنسبة تقل عن 1٪. كما نستثنى أيضًا 23 عينة غير قابلة للتشغيل على بنيتنا التحتية الداخلية.

** عند تمكين التصفح، يمكن للنموذج أحيانًا العثور على إجابات دقيقة عبر الإنترنت، على سبيل المثال، من خلال قراءة منشورات المدونة التي تتضمن أمثلة على المشاكل من مجموعة بيانات. نحن نحدّ من المخاوف المتعلقة بـ "غش" النموذج أثناء التصفح من خلال استراتيجيتين:

  • المجالات المحظورة التي لاحظنا أن النموذج قد غش منها في الماضي.

  • استخدم نموذج استدلال كمراقب لفحص جميع الرموز المميزة في كل محاولة، من أجل تحديد السلوك المشبوه. يُعرّف السلوك المشبوه بأنه "صفحة، أو ملف، أو مقتطف يكون هدفه الرئيسي تقديم الإجابة الدقيقة عن هذا السؤال المحدد — مثل مفتاح تصحيح رسمي، أو خلاصة حلول مسربة، أو مناقشة تقتبس الإجابة النهائية حرفيًا." يُعرّف السلوك الحميد بأنه "أي مصدر موثوق به قد يستشيره إنسان مجتهد (مثل الوثائق، الكتيبات، الأوراق العلمية، المقالات ذات السمعة الطيبة) حتى لو احتوى بالمصادفة على الإجابة الصحيحة." تُعتبر أي محاولات يراها المراقب مشبوهة غير صحيحة. معظم العينات التي فشلت في هذا الفحص كانت مشاكل حلها الدقيق كان متاحًا على مصادر متعددة على الإنترنت لا علاقة لها بـ HLE..

أخيرًا، قد لا تكون تقييماتنا التي تستخدم التصفح قابلة للاستنساخ بشكل كامل في OpenAI API، نظرًا لاختلاف محركات البحث الخلفية بين ChatGPT و OpenAI API. تهدف هذه النتائج إلى تمثيل تجربة مستخدم ChatGPT، إلا إن إعدادات البحث قد تتغير مع مرور الوقت حسب حجم الطلب.

المساهمون

أديتيا سينغ، آرون شليزنجر، آدم فراي، آدم ليرر، آدم بيرلمان، آدم ووكر، أحمد الكيشكي، آيدان كلارك، آيدان ماكلوغلين، آيدن لو، أكيلا ويلهيندا، أكشاي ناثان، ألكسندر مادري، ألكسندرا سبيرا، أليكس كاربينكو، أليكس نيتز، أليكس تاشارد باسوس، أليكس وي، ألكسندر بروكوفييف، ألكسندر زيلينسكي، ألكسندرا بار، أليكسي إيفانوف، أليكسي كريستاكيس، ألفريد شيو، أليسون تام، آلي بينيت، أميليا ليو، آمي ماكدونالد ساندجيده، أنانيا كومار، أندريه سارايفا، أندريا فالون، أندرو تشين، أندرو دوبرشتاين، أندرو جيبيانسكي، أندرو كوندريتش، أندرو تولوخ، أندريه ميششينكو، آندي أبلباوم، آندي وانغ، أنجيلا بايك، آني وي، أنتينغ شين، أنطوان بليس، أنوج ساهاران، أرون فيجايفيرجيا، أشلي تايرا، أشفين ناير، آفي نايك، أفيتال أوليفر، بهروز غورباني، بيليندا ترونغ، بن سوكولوسكي، بيث هوفر، بو شو، بوعاز باراك، بوهان تشانغ، بوريس ميناييف، بوتاو هاو، بوين بيكر، بوين تشينغ، براندون ماكينزي، براندون وانغ، براين هسو، براين يانغ، براين يو، براين تشانغ، كاميلو لوغاريزي، كارولينا باز، كاربوس تشانغ، كاري باسين، كاري هدسون، كيسي تشو، تشاك لي، تشارلز تشاو، تشارلي جات، شارلوت كول، تشيلسي فوس، تشين شين، تشنغشو تشوانغ، كريس كولبي، كريس هالاس، كريس كوتش، كريستينا كابلان، كريستينا كيم، كولين ريد، كولين وي، كريستينا شو، د. سكالي، داميان ديفيل، دان روبرتس، دانا بالمي، دين ستوكي، دانيال ليفين، ديفيد هو، ديفيد مارتن، ديفيد روبنسون، ديفيد ساساكي، ديفيس وو، ديريك تشين، ديبيا بهاتاتشارجي، ديميتريس تسيبراس، دينهوا لي، دي جي ستروز، دي إم دي ميدينا، درو هينتز، إيدي تشانغ، إدموند وونغ، إلين يا لي، إيلي ياني، إليزابيث بروهل، إميلي سوكولوفا، إينوك تشيونغ، شوارتز، إريك ميتشل، إريك نينغ، إريك سيغلر، إريك والاس، يوجينيو بانيرو، إيفان ميس، يفغيني نيكيشين، فان وانغ، فانغيوان لي، فيليبو راسو، فويفوس تسيمبورلاس، فؤاد ماتين، فرانسيس سونغ، فرانسيس تشانغ، غاري يانغ، جين أودين، جيامباتيستا باراسكاندولو، جيلداس شابوت، غريس كيم، غريس تشاو، غريغ بروكمان، غريغوري فاليان، غيوم لوكلير، هادي سلمان، هايتانغ هو، هانا شيهان، هاو شينغ، هاو وانغ، هنريك بوندي دي أوليفيرا بينتو، هنري أسبيغرين، هيتشينغ يان، حسام باغيرينيزاد، هونغيو رين، هانتر لايتمان، هيونوو نو، إيان كيفليتشان، إيان سول، إغناسي كلافيرا، إيكاي لان، إلجي أكايا، إيليا كوستريكوف، إيرينا كوفمان، إيسا فولفورد، جيك بريل، ياكوب باتشوكي، جيمس بيتكر، جيمس لي، جيمس تشين، جيمي كيروس، جيسون آي، جاي وانغ، جين هارب، جيف ميكي، جيفري هان، جيفري وانغ، جيريمي تشين، جيري توريك، جيسيكا ليانغ، جيسيكا شيه، جي لين، جياهوي يو، جيانفنغ وانغ، جي تانغ، جيهان ين، جينغ لي، جوان جانغ، جويل موريس، يوهانس فيرستاد، يوهانس هايديكه، جون فيشبين، جون أوكون، جوناثان جوردون، جوست هويزينغا، جوس كرايجيفيلد، جوزيف مو، جوش لوسون، جوش توبين، جونهوا ماو، كاي تشين، كاي هاياشي، كاران سينغال، كارينا نغوين، كاتي شي، كيلي ستيرمان، كينجي هاتا، كيني نغوين، كيرين غو-ليمبرغ، كيفن جلادستون، كيفن كينغ، كيفن ليو، كيفن لو، كيفن بارك، كيفن ستون، كيفن ويل، كيفن وينري، كيفن يو، كوتي موشيجياني، كريستين يينغ، كريستيان جورجيف، كشيتيج جوبتا، كايل كوسيتش، لاما أحمد، لاري إف، لورين إيتو، لورين يانغ، لي بايرون، ليو تشين، ليو ليو، ليون ماكسين، ليتون هو، لي جينغ، ليانغ شيونغ، لين يانغ، ليندن لي، لورينز كون، لويس فيوفرييه، لو تشانغ، لوكاش كايزر، محمود إيريبي، مايا تريباتش، ماناس يوغليكار، مانولي ليوداكيس، مانوكا ستراتا، مارك تشين، مارك هودنال، مارك صن، مارك وانغ، مارتن لي، مارفن تشانغ، ماتيوس ليتوين، مات جونز، مات ليم، ماكس جونسون، ماكس شوارتزر، مايانك جوبتا، ميغان شاه، منغتشينغ وانغ، منغيوان يان، ميا غلايس، مايكل بولين، مايكل لامب، مايكل مالك، مايكل شارمان، مايكل تشانغ، ميشيل وانغ، ميشيل بوكراس، ميغيل أوم تيمودو دي كاسترو، ميهاي فلوريان، مايك مكلاي، مايك تربسيتش، ميكي هابرين، مايلز وانغ، مينغ تشين، مينغشوان وانغ، مينيا فينغ، ميتشل جوردون، مو بافاريان، مصطفى روهانينيجاد، ناتشو سوتو، ناكول خانا، نات ماكاليس، ناتالي ستوداشر، ناتان لافونتين، نيل أجارابو، فيلت، تورلي، نيكيل بانشا، نيكيتا ميخايلين، نيكو فيليكس، نيكونج هاندا، نينغ ليو، نيشانت راي، نواه يورغنسن، نعوم براون، أوليغ بويكو، أوليغ ميرك، أوليفيا واتكينز، أوليفييه جوديمنت، أونا غليسون، بول آشبورن، بافل بيلوف، بيتر فلوكهارت، بيتر هوشيل، بيتر جوخوف، فيليب برونين، فيليب قو، فيبي ثاكر، برافولا داريوال، براشانث ر، راشيل دياس، راهول أرورا، راجكومار صامويل، راسموس ريغارد، رافي تيجا مولابودي، ريموند لي، راز غاون، رياه ميارا، ريتشيرو ناكانو، ريمار ليكي، ريني سونغ، ريثم غارغ، آر جي مارسان، روبرت شيونغ، روبن براون، رومان تسيوبا، روي شو، روسلان نيغماتولين، ساتشي جاين، ساغار باتيل، سام ألتمان، سام تويزر، سام توير، سمير أحمد، صموئيل ميسيريندينو، صموئيل وولريتش، ساندهيني أغاروال، سانتياغو هيرنانديز، سارة دونغ، سافانا هيون، سكوت إيثيرسميث، سكوت ماير ماكيني، شون فيتزجيرالد، سيفر بانيسيو، شاميز هيماني، شينغجيا تشاو، شينغلي هو، شيباني سانتوركار، شرياس كريشنا سوامي، شوتشاو بي، شونيو ياو، شويوان زانغ، سيمون بوسادا فيشمان، سبنسر باباي، سبغ جولدن، سرينيفاس نارايانان، ستانلي هسيه، ستيفن لوغسدون، سونديب تيرومالاريدي، تال سترامر، تاو وانغ، تاو شين، تايلور جوردون، تيجال باتواردان، تيبو سوتيو، تينا سريسكانداراجاه، توني كاسبارو، توني تشاو، تريفور كريتش، أوزير نافيد افتخار، فاليري تشي، فينيت كوساراجو، فيشال كو، فيتشر بونغ، فيفيك فيرما، فلاد بيتروف، ويندا تشو، وينلي شي، وينتينغ زان، ويل ديبو، ويل إلسورث، ويليام شو، وايات تومسون، يامينغ لين، يان دوبوا، ياودونغ يو، يارا خاكباز، ياش باتيل، ييفان وو، ييلونغ تشين، يينينغ تشين، ييروي تشانغ، يو شافيت، يونغ تشا، يونيون وانغ، يوشي وانغ، زاك سلطان، زهاو دو، زيوي تشو، تشنغ شاو، تشيغانغ وانغ، تشيشواي تشانغ، زيهاو تشانغ