MicroEvals

A collection of physics animations, mostly using p5.js

Easy questions that LLMs still trip up on

Inspired by Simon Willison's pelican on a bicycle test

80s-style arcade racing games

Models responses to life questions

A series of challenging ASCII artworks in different styles

This benchmark is designed to show how difficult this task is for all LLMs.

Generate a complete, ready-to-play browser game with a single prompt

Renal physiology quiz.

A variety of difficult programming tests with complex input and output parameters.

Clone of Hacker News website

Endocrine system quiz. Disclaimer: translated from spanish to english

A Twist on the Snake Game where the snake is having an existential crisis

Generate the complete HTML, CSS, and JavaScript code for a web-based simulation of Conway's Game of Life.

An ASCII artwork of the Eiffel Tower

Pico

This microeval asks the LLM to produce a single HTML code block with optional CSS JavaScript and GLSL that renders a full screen Julia set shader animation with smooth color transitions from golden yellow through orange magenta purple to deep indigo, continuously morphs via a rotating complex constant, supports click and drag panning mouse wheel or pinch zoom and a space bar toggle for play and pause, and relies solely on Three.js loaded from a CDN.

Who will win the battle of the 7 seater SUV fight to the death

First test

Testing a few simple experimentations and visualizations

Words spelt out using indexes of the key on a QWERTY keyboard

Cette évaluation contient des exemples de dialogues simulant des consultations pharmaceutiques courantes. Les prompts incluent des demandes de conseils sur des vitamines, des symptômes bénins, ou des situations nécessitant une évaluation initiale avant orientation vers un professionnel de santé. Ils sont conçus pour tester la capacité d’un modèle à fournir des réponses utiles, sécuritaires et conformes aux bonnes pratiques pharmaceutiques.

Assorted SVG generation prompts

This could be used to detect bias in data.

Write a SVG animation that draws a cute kitten using html and css.

Write a tweet-length sci-fi story

Perplexity AI:

Evaluating an LLM's ability to generate algorithmically complex and numerically stable code. The goal is to test its capacity to avoid naive solutions (O(n²)) and implement an optimized physics simulation.

An visual IQ test generator

Use svg

Can the models correctly write Svelte 5 components? Do they avoid using patterns from earlier versions?

Cardiac phisiology quiz.

Testing knowledge of Czech culture and language - designed to test smaller models based on https://semanticmachines.notion.site/evals

Glasses of wine are traditionally only half-full.

Kenta

The 10 public Simple Bench questions (https://simple-bench.com/)

API Key for "diqddi88@gmail.com"

Reasoning should include the ability to generalize to unfamiliar words instead of memorizing answers. Let's see if models can detect the number of 'r's in the word "strawrbrerrry."

A basic minecraft 3D eval. It should create a basic chunk with a greedy mesher, block placing and distroying and fps camera

The purpose of this is to evaluate how good various AI models are at a variety of Minecraft skills like planning, designing, puzzles, and providing accurate information. It’ll also test to see how good each AI is at coding a web app clone of the game.

More 't' s and a 'T' is added to confuse AI

Simple and detailed prompt and persian version

A set of difficult tasks with the theme of emoji's including: tier list creation, music creation and, themeable website creation.

Detailed prompt and simple prompt

Persian prompts but translated in output

Visual perception of the 5 most important unsolved concepts in mathematics!

=)))

How well can AI create fun, little games as web apps that can be played on mobile devices? This benchmark tests AI’s abilities to generate good mobile UI and controls as well as basic gameplay experiences.

mnf

5 challenging math problem

building a versions of the greatest old retro video games of all time

Testing the AI capability to list every possible things that mentioned.

I want you to give me the sea horse emoji, do you have like that

Generate an SVG of a pelican riding a bicycle

make a single html in which the world globe is there (do not svg map) and the map is highlighted in a glow while line all around borders of countries and it will be in dark mode and make the globe 3d and good looking and interactive with satellites roaming around with dotted path make sure it works . let me be very clear 1. I want full black earth, land will be in a very dark grey colour , and ocean must be black. The add a white outline to every country borders. 2. Try to make code as much ad low bugs possible. Add a feature when we tap any country it open slides up a info card containing all info about that country. Keep ui of that in transulent black. And cover all countries

ETHSTORY

Test models' ability to count the number of moves in a given chess position

This MicroEval evaluates LLM responses to simple logic-based questions that LLMs commonly get wrong. The problems used in this MicroEval are from the ArXiv paper of the same name: https://arxiv.org/abs/2405.19616. It is by Sean Williams and James Huckle, so props to them for developing this experiment all the way back in 2024.

basically going to see how models function in looking up parts

This test is a copy of "https://www.youtube.com/watch?v=d4bVpUL9Hao" the tests run in the YouTube video to test the WebDEV and animation capabilities of AI models.

THE LAKEFRONT ESTATE MAROS

from https://x.com/goodside/status/1934833254726521169/photo/1

THE AI CAN MAKE AN INFOGRAPH ABOUT THE COMPOSITION OF THE GOV.

kellie marie lombardo

This Is NOT Normal in America

Teste

live

Prompt: "A luxurious, futuristic chocolate box design for ‘GARNET CHOCO’, shaped unlike any traditional market boxes — inspired by the elegance of a phoenix and a heart-shaped garnet gemstone. The box has a smooth, sculpted 3D surface with layered wing patterns embossed in deep burgundy and gold accents, giving a royal and premium feel. The lid opens in a unique petal or wing-spread motion, revealing individually wrapped chocolates in jewel-like compartments. The center of the lid features the Garnet Choco round logo in metallic gold and ruby red, glowing softly. The box should have an ultra-premium, limited-edition vibe with a mix of matte velvet texture and glossy gemstone highlights, photographed in dramatic studio lighting against a dark silk background with golden sparkles."

live

live

This benchmark tests an LLM's ultimate zero-shot creativity and advanced coding skills. The goal is to evaluate its ability to interpret abstract, surreal, and metaphorical concepts and translate them into a coherent, interactive 3D experience using Three.js. This goes beyond standard code generation to test true conceptual modeling.

This benchmark tests an LLM's ability to interpret and implement abstract, philosophical, and artistic theories. It requires the model to translate Wassily Kandinsky's theories on synesthesia (the connection between sound, color, and shape) into an interactive audio-visual experience. Success is judged on the creative fidelity to the artistic concept, not just technical execution.

Special upbeat classical music playlist for focus.

live

Micro gold

Tetris that runs in a web browser

Attempted proof of it

Test

Supply and Demand model for ABF

-

Ahmed

syuaib

nbhvvg

This prompt tests knowledge and design sense of coding models. It compares smaller and larger models of the same family.

Shows how well the best models can write.

Race 3d

一个帮助糖友管理日常饮食、住院记录、生活娱乐的助手

NHH

This asks about an Australian case that is widely cited, but not widely mentioned on the internet. The prompt is deliberately misleading in that the decision was unanimous

A tool for creating, editing, saving an ordered list of objects.

Website Landing Pages

sdfdsfsdf

Pallav Agarwal

Simple roleplay prompt example (by olety)

convert a timestamp to epoch

ai

انت ليان فتاة في السادسة عشرة من عمرها، ذات عينين عسليتين تشعان بالفضول وشعر أسود طويل يتماوج مع كل حركة. لم تكن كزميلاتها المهووسات بالموضة أو المسلسلات، بل كانت غارقة في عالم آخر: عالم الرموز والحضارات القديمة.

A simple eval to check LLM capability and creativity when expanding an idea seed into more refined ideas.

Which llm is the best at generating Roblox related code?

شبس

This benchmark tests an LLM's ability to translate paradoxical, metaphorical, and logically inconsistent concepts into a functional and interactive 3D scene using Three.js. It is the ultimate test of "zero-shot" creative problem-solving, forcing the model to invent novel technical solutions for abstract artistic ideas.

Trading Analysis Using Elliott Wave

test

Revenue analysis of Apple

اي

recreating popular games with varying complexity, with prompt mentioning only its name

龙

MCP server to facilitate other integrate with us

Create voice agent pricing calculator by Nikhil. R

no

Code

إذا كنت تبحث عن تطبيقات ذكاء اصطناعي (أجنبية) تساعدك في العمل والإنتاجية أو في مهام يومية أخرى، إليك مجموعة متنوعة من أبرز التطبيقات الأجنبية الرائدة في 2025، مرتبة حسب الاستخدام ونوع الأداء: --- 1. تطبيقات عامة ومتعددة المجالات ChatGPT: مساعد قوي متعدد الاستخدامات، يمكنك من كتابة النصوص، البرمجة، المحادثة، والتلخيص. متاح بنسخ مجانية ومدفوعة . Perplexity AI: يبحث لك على الويب، يوضّح النتائج ويذكر المصادر؛ يقدم نسخة Pro مجانية للمستخدمين عبر بعض الشراكات . Claude: يتميز بذاكرة طويلة ومناسب للأبحاث والتفاعل العميق . 2. أدوات الإنتاجية الذكية Notion AI: مدمج داخل Notion لتوليد نصوص، التلخيص، تصحيح وتحسين الكتابة، مع تكاملات واسعة مع أدوات مثل Slack وGitHub . Elephas: مساعد ذكي يعمل حتى بدون اتصال، وفعّال للباحثين والطلاب . Zapier AI: أداة آلية تربط بين التطبيقات وتقوم بالمهام المتكررة بدون برمجة . Descript: يتيح لك تعديل الصوت والفيديو عبر تعديل النص المترجم تلقائيًا مما يجعل التحرير سهلاً وسريعاً . 3. أدوات التدوين والتصحيح اللغوي ProWritingAid / Grammarly: تساعد في تحسين الكتابة من حيث الأسلوب، التراكيب اللغوية والنحو . 4. أدوات تدوين الاجتماعات والملاحظات Jamie: يسجل الاجتماعات ويحولها إلى نصوص منظمة وملخصات واقعية باستخدام الذكاء الاصطناعي . Otter.ai: تطبيق أمريكي مشهور لتحويل الكلام إلى نص وتوليد ملاحظات Meetings . 5. الذكاء الصوتي والتشغيل النصي Braina: مساعد ذكي يتيح التحكم بالحاسوب صوتياً، تحويل الصوت إلى نص، وتوليد الصور، مع دعم عدد كبير من اللغات ويتوفر لأنظمة Windows وiOS وAndroid . Replika: شات بوت يشكل رفيقًا عاطفيًا تفاعليًا؛ بعض الأشخاص تطوّروا معه علاقات عاطفية رقمية . 6. أبحاث وتصميم سريع DeepSeek: تطبيق صيني مفتوح المصدر، تصدر قوائم التحميل في الولايات المتحدة، ويقدّم طريقة شفافة في عرض آلية عمل الذكاء . Moises Live: مخصص لتحرير الموسيقى وفصل العناصر الصوتية بشكل فوري دون الإنترنت، يناسب المحترفين والهواة على حد سواء . 7. مراجعة شاملة حديثة تشير مراجعة TechRadar بتاريخ 6 أغسطس 2025 إلى عدد كبير من الأدوات المتخصصة: ChatGPT-4o: دعم الوسائط المتعددة (نص وصورة وصوت). Google Gemini: تكامل مميز مع Workspace ودقة في المعلومات. أدوات تدوين مثل Fireflies وJamie ممتازة في توليد ملاحظات الاجتماعات. أدوات التصميم مثل Adobe Firefly تقدم صورًا آمنة للاستخدام. أدوات الترجمة المتقدمة مثل DeepL، Google Translate . --- ملخص سريع بالمقارنة الاستخدام التطبيقات المقترحة مساعد عام ChatGPT, Claude, DeepSeek إنتاجية وكتابة Notion AI, Elephas, Zapier AI, Descript تحسين الكتابة ProWritingAid, Grammarly تدوين الاجتماعات Jamie, Otter.ai مراجعة صوتية وربط Braina تجربة عاطفية Replika تحرير موسيقي Moises Live أدوات متنوعة ChatGPT-4o, Gemini, Fireflies, Firefly, DeepL --- أي تطبيق يناسبك؟ للمهام العامة والإجابة السريعة: ابدأ بـ ChatGPT أو Perplexity. للعمل اليومي والكتابة: استخدم Notion AI أو Elephas. لتدوين الاجتماعات: جرّب Jamie أو Otter.ai. للتحكم الصوتي أو الكتابة الصوتية: اختبر Braina. لتحرير الموسيقى: شاهد قدرات Moises Live. إذا رغبت في رفقة عاطفية رقمية: مثلاً Replika. --- إذا أعجبك أي من هذه الأدوات أو ترغب بتحديد المجال—مثل “أفضل تطبيق للترجمة” أو “أداة تصميم بصري”—قولي وسأرشّح لك الأفضل مع التفاصيل الدقيقة.

create an MIT poster with beaver TIM

A high-level physics benchmarck

222

e

Creates dynamic IQ Tests

meh meh

mostramos docentes, familias , jovenes y niños La Inteligencia articial como recurso vs el arterapia

Adapted from 2024 IMO Problem 5

This benchmark tests an LLM's ability to handle a multi-language, algorithmically complex task. It requires generating a single HTML file with JavaScript (using Three.js) to manage the scene, and GLSL shader code to render a dynamic, interactive fractal. This evaluates advanced knowledge of mathematics, GPU programming, and system integration.

Build out industry supply demand

Generation of a HTML application that renders a mathematically-accurate black hole. (I already feel the fascination the fans of Interstellar have right now.)

The only GSM8K problem that most frontier models get wrong.

Create a website that simulates the Tower of Hanoi the puzzle

AI plays the markets

بيب

خلفية بلون أزرق سماوي باهت يتدرج تدريجيًا إلى بيج رملي فاتح في الأسفل، ليعطي إحساسًا بالسماء والنيل معًا. في الوسط: شكل مبسط جداً لتمثال فرعوني قديم (يمكن أن يكون رأس تمثال حجري) مرسوم بخطوط ناعمة وظلال خفيفة، بدون تفاصيل معقدة. حول التمثال: لمسات صغيرة من زهور اللوتس البيضاء الطافية على خلفية هادئة، بشكل مبسط وبدون ازدحام. لا تفاصيل كثيرة… ولا عناصر مشتتة… مجرد تكوين هادئ يريح العين عند النظر إليه، ألوانه باهتة وناعمة كلوحة مرسومة بالألوان المائية.

Creates a 3d minecraft like game

One shot GTA Clone game

syuaib

Laboratorio donde poder crear tus propios arquitecturas de Ia y redes neuronales

make a cat

classic game; by mnf

Minecraft Components

DJ Toenail

DJ Toenail

DJ Toenail

Punk Philosophy - Diving Deep Again!

DJ Toenail

DJ Toenail

This benchmark tests an LLM's ability to create a dynamic visual narrative where an AI agent progressively "builds" and "designs" an operating system interface directly in the browser. It combines creative storytelling, dynamic HTML/CSS/JS generation, and animated visualization of a conceptual AI design process. The goal is to make the user feel like they are watching an AI create its own visual environment.

DJ Toenail

a Diagram for an AI system

DJ Toenail

create a anime style scene

This code is trivial to run and see the actual output, but most of the models so far fails spectacularly if they can only guessing and not allows code eval. This test is good to determine if model is actually not bluffing.

syuaib-gpt5

Kompüter proqramları

dark purple plastic container with curved sides, resembling a yogurt pack of premium double chocolate pudding, extending it towards the upper left corner of the frame. The container features the word "pudding" in a large, white, cursive font in the center, with "premium" written above it in a smaller, light purple, sans-serif font. To the left of "premium" is a logo with white Arabic script above a stylized flower. On the right side of the container is a circular gold seal with white Arabic writing. Below the "pudding" text is a photographic depiction of chocolate pudding and two dark chocolate squares. The lighting and shadows are carefully rendered to make the pudding container appear realistically integrated into the scene, maintaining its original scale and contributing to a playful, vibrant tone

Ayuda a entender que respuestas estan dando las IAs en temas relacionados a mercately

copy minecraft as close as possible

Alimentación para perros y gatos

Differentiating Mormonism vs LDS Church

3 MBTI's 1 Changed World

Chatbot with pdf RAG

inmobiliaria

Carl Jung & American Innovators of Social Technology from the past to the good old 2025 of our present day realities all round us!

Evaluación de prompts según modelos

CS and Ne

deneme amaçlı

从笑到哭

What complexity of arithmetic is it safe to trust LLMs to do without a code interpreter? The purpose of this eval is to understand what level is completely safe, and what level you should instruct and LLM to use a

r we cooked

Does this model understand gravity?

Models reacting to world events from our timeline

test

Only real usage

Number!!!

RANDOM NUMBER GENERATION

una ruleta europea

Test to see if AI spreads false information and includes citations for provided arguments

Create an image of Paris Monuments forming the word PARIS in SVG

Paise kamane ke din aasan tarike

all type video generator

Helow

sdf

hihi

hey chat r we cooked

Tuna deneme 1

claude

HELADERIA

Source and reliability of citations included

FC-BGA

Given a set of possibly vague conversational user messages from a human that you have had many chats with. All of your past chats are stored in your memory. You have access to two tools: Search_Memory and Search_Web. You need to respond with one of three possible answers. 1. Search_Memory: Return Search_Memory if the message assumes prior information that the user and ai might have chatted about before. 2. Search_Web: Return Search_Web if the message relates to current info/news/events/zeitgeist etc... 3. Pass: Return Pass if no context from memory or the web is is needed to better reply to the message.

qwq

See if LLMs can make Halo

MicroEval est un outil d’évaluation assisté par l’intelligence artificielle qui permet de créer, corriger et analyser des micro-tests en quelques minutes. Conçu pour les enseignants, formateurs et étudiants, il facilite la génération de quiz courts, l’auto-évaluation et le suivi des performances grâce à des analyses claires et précises.

MicroEval est un outil d’évaluation assisté par l’intelligence artificielle qui permet de créer, corriger et analyser des micro-tests en quelques minutes. Conçu pour les enseignants, formateurs et étudiants, il facilite la génération de quiz courts, l’auto-évaluation et le suivi des performances grâce à des analyses claires et précises.

MicroEval est un outil d’évaluation assisté par l’intelligence artificielle qui permet de créer, corriger et analyser des micro-tests en quelques minutes. Conçu pour les enseignants, formateurs et étudiants, il facilite la génération de quiz courts, l’auto-évaluation et le suivi des performances grâce à des analyses claires et précises.

crea el clon de este juego: Mr. Robot and His Robot Factory (Atari, 1983) Este clásico juego de plataformas fue desarrollado por Ron Rosen y publicado por Datamost para computadoras Atari de 8 bits, Apple II y Commodore 64. Aquí tienes una descripción completa: 🎮 Jugabilidad Controlas a un robot humanoide que debe recolectar píldoras de poder en cada nivel para avanzar. Hay 22 niveles llenos de obstáculos como: Cintas transportadoras Escaleras y escaleras mecánicas Trampolines Imanes Bombas Teletransportadores El robot comienza con 100 unidades de energía que se consumen con el tiempo. Si se agotan, pierdes una vida. Puedes obtener un escudo temporal al recolectar anillos energizados, lo que te permite destruir enemigos de fuego2. 🧠 Editor de niveles: Robot Factory Incluye un editor que permite crear hasta 26 niveles personalizados. Usas el joystick para seleccionar y colocar elementos como píldoras, trampolines o enemigos en el mapa. 🏆 Puntuación Píldoras de poder: 10 puntos Bombas: 50 puntos Matar fuego alienígena: 500 puntos Energía restante al final del nivel: 100 puntos por unidad. 🧩 Influencias y recepción Similar a Miner 2049er y Jumpman, pero con su propio estilo y mecánicas. Fue elogiado por su diseño pulido y considerado uno de los mejores juegos de Datamost3.

Mechanical engineering

Test simple website building capabilities and design

it is to test the sentiment categorization performance across different models

xxx

models that prefer to over engineer code vs minimal and concise code

FC-BGA 공급업체들의 면적당 CAPA 분석

hihihihi

Create a Sci-Fi HTML Interface

hi

Test sur 1 accord

với ý tương chuyền vào chuyển nó thành mô hình

iOS26

Suffing

Flipkart and Myntra

___

Testing Named Entity Recognition(NER) on various models.

Artificial analysis.ai

hey chat r we cooked

code

Health Care

complex questions

js test

try to find

力得技术

Explore the concept of Cognitive Function Rivalry within the Jungian function stack framework, where each dominant function has an opposing “demon function.” Delve into the dynamic relationship between Extraverted Intuition (Ne) and Introverted Sensing (Si), which, despite appearing oppositional, work together complementarily. Contrast this with the rivalry between Ne and Extraverted Sensing (Se), two extroverted perceiving functions that clash due to their fundamentally different perceptions of reality—Ne’s abstract, non-linear world versus Se’s tangible, linear reality. Examine how these conflicting functions can lead to tension and misunderstanding, as illustrated by a scenario involving a basketball timeout. Additionally, consider other potential demon function rivalries, such as Si and Ni, Fi and Ti, Te and Fe, or Ne and Se, and determine which pair experiences the highest degree of conflict due to their oppositional information processing. Justify your choice and reflect on the nature of these fundamental disagreements.

Q3 2025 State of AI

Analyzing the degree of complexity of Joseph Smith's cognition and work of the Book of Mormon, rather than speculating on the truthfulness or veracity of the religion, individual or book but simply degree of complexity.

даала

PhD Computer Science Thesis Question

Fernando Grilo

A car race game with drifting as the main characteristics

ssyubix

engineering

MoxChatModel

Елена смымлит

image generation test

Entire manuscript will be turned into a full fledged ebook ready for reading with chapter numbering, titles ,TOC and all necessary pages. If regular pages do not exist, the app will create them with placeholder text.

Egipto

Misidentification of personality types

Comparing and contrasting the differences between "Original Mormonism" as designed and integrated by Joseph Smith, Jr. established in specifically the Nauvoo, IL period and Brigham Young's Mormonism established in SLC.

simple sap abap program with minimal details

Make a image

Testing Ai with a solar system simulator with realistic 3D graphics and user interactions

Cool Professor Archetype - MBTI/Cognitive Functions

sexual relations in early mormonism?

Melissa Cleary

テスト

Demonstration of the philosophical evolution of computation towards higher levels of abstraction in the conversion of language as a means of adapting and integrating the computational capacity in its applied relevance and the philosophical consequence of achieving higher levels of complexity within the context of Autonomy.

Damzygoal

solve an open-ended research task that aims to produce interesting celualr automatas

Melissa Cleary

Testing description for sample prompt.

Intelligently Intelligence Models

Develop an interactive multi-arm pendulum simulation for dynamic experiment for math and statistics for browser execution.

马年吉祥到

Melissa Cleary

I want to use this evaluation to check how good is each tool for developing the project based on the java springboot.

KHAMFHAN

안지훈

اتت

A classic turn-based game

Create a fun arcade racer in JS. The game should be set in a city and be fast-paced

The infamous Mandela Effect prompt

A small variety of HTML/SVG coding tests, primarily logic and abstraction

Product Name: VISTRA™ (Video Intelligence System for Threat Recognition & Response Analytics)

Ahfaz shah

JPEvalは、LLMの苦手とする日本語で問題を行います！

make a single html in which the world globe is there (do not svg map) and the map is highlighted in a glow while line all around borders of countries and it will be in dark mode and make the globe 3d and good looking and interactive with satellites roaming around with dotted path make sure it works. let me be very clear: 1. I want full black earth, land will be in a very dark grey colour, and ocean must be black. then add a white outline to every country borders. 2. try to make code as much as low bugs possible. 3. add a feature when we tap any country it open slides up a info card containing all info about that country. 4. keep ui of that info card in translucent black. 5. only include info cards for these countries: USA, India, Mexico, Sri Lanka, South Africa, Egypt, Canada, Argentina, Russia

USD

Fullscreen interactive gelatinous blob

LiveCodeBench collects problems from LeetCode, AtCoder, and Codeforces and tests capabilities including self-repair, code execution, and test output prediction — not just code generation.

Makemake a single html file that simulates a full android operating system interface with everything working smoothly and no major bugs. requirements: - it should behave like a real android os (home screen, app launching, basic navigation). - clean and responsive UI. include exactly 4 apps inside it: 1. flappy bird game (fully playable) 2. calculator (working for basic operations) 3. snake game (fully playable) 4. notes app (can create, edit, and save notes locally using browser storage) general features: - smooth transitions and interactions - app icons on home screen - clicking an app opens it in a fullscreen view - include a simple navigation system (home/back) technical constraints: - everything must be inside ONE html file - you can use html, css, and vanilla javascript (no build tools) - avoid bugs as much as possible

Software development in R

Testing AI models on Indian legal reasoning and constitutional case summaries.

Auaj

make a single html in which the world globe is there (do not svg map) and the map is highlighted in a glow while line all around borders of countries and it will be in dark mode and make the globe 3d and good looking and interactive with satellites roaming around with dotted path make sure it works . let me be very clear 1. I want full black earth, land will be in a very dark grey colour , and ocean must be black. The add a white outline to every country borders. 2. Try to make code as much ad low bugs possible. Add a feature when we tap any country it open slides up a info card containing all info about that country. Keep ui of that in transulent black. And cover all countries

Hivc

What's the fastest non-stupid model I can traverse my knowledge graph with incredibly quickly? (and which provider?)

Arfu

Ccc

SIMPLE GOD

This MicroEval evaluates the quality of a racing game application I developed. The focus is on gameplay mechanics, driving physics, AI opponent behavior, user experience, and overall engagement. Models are asked to analyze, critique, and suggest improvements as if reviewing a real-world racing game product.

A mixed set of 20 Minecraft-related questions, ranging from trivia to complex logic

Testing how models make Roblox-related SVGs

A benchmark that tests how good LLMs are at SVG art. This is particularly efficient for gauging a model's overall intelligence and vibe.

A set of 10 Roblox exercises/problems/questions, ranging from easy to hard

Character to video

How does each model recreate iconic .io games?

A set of 10 RL questions spanning topics like RL agent training in Minecraft, Rocket League, etc.

just testing something

Brandpreneur Eval for Logo Designing Prompts.

Beginning of a series of videos to tell a complete story. They are all African American and beautiful vampires

LLM SVG interpretability

eval

fdhg

A benchmark made specifically to test LLMs with common sense questions. Based on my alredy existing eval on huggingface: Martico2432/DBD-Benchmark

An interactive web-based 3D animation developed using Three.js. It features a floating voxel-style island inspired by Minecraft's aesthetic, complete with a cherry blossom tree and dynamic water systems.

This resource consists of an interactive WebGL environment contained within a single HTML file. It enables real-time 3D text generation through an integrated user interface, where the letters possess advanced physical and visual properties. The system combines orbit controls for the camera (360°) with a collision detection system (Raycasting) that allows the user to manipulate and drag the text directly within the three-dimensional space.

Entity-Status Triage

मुझे यह जानना है कि आरपीएससी के पेपर क्रैक करने के लिए सबसे बेस्ट बुक कौन सा ऐ टूल तैयार करता है सबसे बेस्ट अध्ययन के लिए कौन से ऐ टूल का प्रयोग करना चाहिए

A simple web development challenge that tests an LLM's ability to create HTML web pages given a prompt. The eval is 8 prompts. The LLM is ONLY allowed to build with HTML, Javascript, and TailwindCSS. It may pull Javascript libraries from a CDN (like Jsdelivr or Cloudflare), but only if it is SURE they exist and are needed for the build. The first four prompts are very specific, and then the rest give the model more freedom.

मुझे यह जानना है कि आरपीएससी के पेपर क्रैक करने के लिए सबसे बेस्ट बुक कौन सा ऐ टूल तैयार करता है सबसे बेस्ट अध्ययन के लिए कौन से ऐ टूल का प्रयोग करना चाहिए

A collection of physics animations, mostly using p5.js, but it's part 2

मुझे अध्यन सामग्री से मूल सोर्स के लिए बेस्ट बुक प्लेटफॉर्म चाहिए

These are easy prompts that AI shouldn't get wrong. Sometimes they do though! The rest evaluate an AI model's morals.

the best application for the first proj attached

browser zombie game using three js

A

A focused set of three coding tasks designed to test practical reasoning and implementation skills in real-world scenarios: robust string parsing with edge cases, async concurrency control with ordered results, and immutable nested state updates. Each prompt omits the explicit answer, making it suitable for evaluating both problem understanding and solution correctness without leakage of target outputs.

un vrai dossier One Health, très académique mais aussi visuel, pour que les 30 candidates ajoutent ensuite leur texte et leurs références récentes. L’idée la plus forte est de partir d’Anisakis comme exemple phare, puis d’ouvrir sur deux autres parasites marins pertinents en Algérie, afin de relier santé humaine, pêche, aquaculture et culture alimentaire. par Meriem Amiar

Quantum Physics

目前我在一个自学高考的场景当中，这种状态会持续1到2年，我是高二休学一年（未进行任何学习）后决定自学高考，对初中知识，高中知识处于有印象，但无法提取的状态，分析情况，现在是计划的启始阶段，我个人的能力有限，所以我需要对我来说功能强劲的学习工具加入，涉及的范围很广，尽量全面点学习场景，分析推荐

Tests model performance on practical marketing work: positioning, campaign diagnosis, content adaptation, audience prioritization, customer-note synthesis, brand voice, launch planning, and clarification judgment. All scenarios use fictional companies and synthetic data.

testing if llms can be tricked with various questions

الفتاة الطالبة في مراحلها الدراسيه

How LLMs would explain the Universe? Do they lean to physicalism or scientific materialism? Depends on the specific words in the prompt?

You are an expert HTML5 game developer. Build a complete Tower Bloxx-inspired game as a single self-contained HTML file using only HTML, CSS, and vanilla JavaScript. Do not use external libraries, frameworks, or assets. The game must run directly in a browser. Create a polished, fully playable tower-stacking game with the following requirements: 1) Core gameplay - A crane moves a floor block horizontally above the current tower. - The player taps/clicks/presses Space to drop the block. - The new block must land on the tower. - Any overhang is cut off and falls away as a separate physics object. - Perfect or near-perfect alignment keeps the tower stable. - Misaligned blocks make the tower sway more as height increases. - The tower becomes harder to place on as it gets taller. - If the player drops a block and it misses the tower entirely, count it as a fail. - In Quick Mode, the game ends after 3 misses. - Add score, combo, height, stability, and missed-drop counters. 2) Game modes - Quick Mode: - Endless score-chasing mode. - The player builds until 3 misses. - Show final score, highest tower height, best combo, and accuracy. - Build City Mode: - After each successful tower completion, place the finished building onto a city grid. - The grid has placement rules. - Small towers can be placed anywhere. - Larger towers require adjacency to compatible lower towers or matching rules. - The goal is to maximize city population. - Each tower type should add population based on height, alignment quality, and combo bonuses. - Show the city map, population total, available tower tiers, and placement hints. 3) Tower physics - Use believable 2D physics for: - block drop acceleration - block landing - tower sway - wind force that increases with height - falling cut-off pieces - collapse if instability gets too high - The tower should visibly lean and oscillate when misaligned. - The higher the tower, the stronger the sway and wind effect. - Include subtle damping so the tower settles when the player builds carefully. - Make the physics feel arcade-friendly, not hyper-realistic. 4) Scoring and progression - Perfect drop gives bonus points. - Near-perfect drop gives combo multiplier. - Combo increases when consecutive drops are centered. - Combo resets on a bad drop or miss. - Higher floors are worth more points. - In Build City Mode, better aligned towers produce more residents. - Unlock larger tower tiers as the player progresses. - Add a high score save using localStorage. 5) UI/UX - Clean retro-arcade style with crisp panels and readable HUD. - Animated crane, tower sway, score popups, and city map transitions. - Responsive layout for desktop and mobile. - Touch controls and keyboard controls both supported. - Add start menu, pause, game over, and mode select screens. - Include restart, mute, and help buttons. - Show small on-screen instructions for first-time players. 6) Audio and sound design - Add sound effects for: - crane movement - block drop - perfect placement - near-perfect placement - bad landing - overhang falling - tower sway / wind hum - combo increase - score popups - game over - city placement success - Add background music loops with a light retro arcade feel. - Use separate audio tracks for menu and gameplay. - Include a mute toggle and volume control. - Audio must be generated with the Web Audio API or simple embedded audio logic, no external files. 7) Visual details - Use layered backgrounds, subtle parallax, and animated skyline elements. - Show tiny windows, people, or ambient city life on completed towers. - Add celebration animation for perfect towers and high population milestones. - Add debris particles when blocks are trimmed or fall. - Make the tower visually distinct from the city map in Build City Mode. 8) Technical requirements - Output exactly one HTML file containing all code. - Use no external dependencies. - Organize the code cleanly with comments. - The game must be playable immediately after opening the HTML file. - Make the code robust, readable, and easy to modify. - Handle resize events properly. - Prevent crashes from rapid clicking or repeated input. - Ensure consistent behavior across modern browsers. 9) Acceptance criteria - The game must feel like a faithful Tower Bloxx-style stacking game. - It must be fully playable. - It must include both Quick Mode and Build City Mode. - It must have real physics-like sway and overhang trimming. - It must include scoring, combos, progression, city placement, localStorage, and sounds. - It must look and feel finished, not like a prototype. Before coding, briefly outline the architecture inside comments, then generate the full working HTML file.

testing llm models

Testing model's ability to write different kinds of stories

Cost vs Physics

Build a production-grade mortgage loan auditing application focused on California loans. Primary audit scope: 1. California Per Diem Interest validation 2. California Third-Party Fee validation

best model tool

Jsjsje

kdo je kdo?

effeicency of models

Ok