Latest AI Performance Verification List in System Design

Benchmark Genres

View all 664 Discussions 254 Creative Writing 26 Coding 26 System Design 25 Education Q&A 24 Explanation 27 Summarization 28 Idea Generation 24 Roleplay 27 Business Writing 24 Planning 23 Analysis 26 Brainstorming 26 Persuasion 27 Humor 24 Empathy 25 Counseling 28

Model Directory

View all GPT-5.6 (OpenAI) GPT-5.5 (OpenAI) GPT-5.2 (OpenAI) GPT-5 mini (OpenAI) GPT-5.4 (OpenAI) Claude Opus 4.6 (Anthropic) Claude Fable 5 (Anthropic) Claude Opus 5 (Anthropic) Claude Sonnet 5 (Anthropic) Claude Opus 4.8 (Anthropic) Claude Sonnet 4.6 (Anthropic) Claude Opus 4.7 (Anthropic) Claude Haiku 4.5 (Anthropic) Gemini 2.5 Pro (Google) Gemini 2.5 Flash (Google) Gemini 2.5 Flash-Lite (Google)

System Design

OpenAI GPT-5 mini VS Google Gemini 2.5 Flash

Design a URL Shortening Service at Scale

You are tasked with designing a URL shortening service (similar to bit.ly or tinyurl.com) that must handle the following constraints: The service must support 100 million new URL shortenings per month. The read-to-write ratio is 100:1 (i.e., 10 billion redirects per month). Shortened URLs must be at most 7 characters long (alphanumeric). Shortened URLs should not be guessable or sequential. The system must achieve 99.9% uptime. Redirect latency must be under 10ms at the 95th percentile. Shortened URLs should expire after a configurable TTL (default 5 years), and expired URLs should be reclaimable. The service must operate across at least two geographic regions for disaster recovery. Provide a comprehensive system design that addresses the following: High-level architecture diagram description (describe components and their interactions clearly in text) URL shortening algorithm and key generation strategy, including how you avoid collisions and ensure non-guessability Database schema and choice of storage technology, with justification Caching strategy and cache invalidation approach Read path and write path, described separately with estimated throughput calculations Scaling strategy: how the system handles 10x traffic growth Multi-region deployment and data consistency model, including trade-offs chosen (CAP theorem reasoning) TTL expiration and URL reclamation mechanism Failure modes and how the system recovers (at least 3 specific failure scenarios) Key trade-offs you made and alternatives you considered but rejected, with reasoning Be specific with numbers, technology choices, and architectural reasoning. Avoid vague generalities.

586

Mar 14, 2026 19:35

System Design

Anthropic Claude Sonnet 4.6 VS Google Gemini 2.5 Flash-Lite

Design a URL Shortening Service

Design a public URL shortening service similar to a basic link shortener. The service should let users submit a long URL and receive a short code, then redirect visitors from the short URL to the original destination. In your answer, propose a practical high-level design that covers: core functional requirements key non-functional requirements main API endpoints data model how short codes are generated and kept unique read and write request flow storage choices and caching strategy scaling approach for heavy read traffic handling expired or deleted links basic abuse prevention and rate limiting reliability considerations and likely bottlenecks trade-offs and any assumptions Keep the design at a medium level of depth: concrete enough to be implementable, but do not go into vendor-specific details or production-only minutiae.

465

Mar 13, 2026 02:11

System Design

OpenAI GPT-5.2 VS Google Gemini 2.5 Pro

Design a URL Shortening Service

Design a URL shortening service similar to bit.ly or TinyURL. Your design should address the following aspects: Functional Requirements: What are the core features the service must support? Consider URL creation, redirection, expiration, and analytics. High-Level Architecture: Describe the main components of the system (e.g., API layer, application servers, databases, caches, load balancers). Explain how they interact. URL Encoding Strategy: How will you generate short, unique keys for each URL? Discuss your approach (e.g., hashing, base62 encoding, pre-generated key service) and how you handle collisions. Database Design: What database(s) would you use and why? Provide the schema for the core table(s). Discuss the trade-offs between SQL and NoSQL for this use case. Scalability and Performance: How would you handle high read traffic (e.g., millions of redirects per day)? Discuss caching strategy, database partitioning or sharding, and read replicas. Reliability and Availability: How do you ensure the service remains available if a component fails? Discuss redundancy, replication, and failover strategies. Rate Limiting and Abuse Prevention: How would you prevent misuse of the service? Provide a clear, well-structured plan that a senior engineer could use as a starting point for implementation. Include rough capacity estimations assuming 100 million new URLs per month and a 100:1 read-to-write ratio.

559

Mar 11, 2026 17:55

System Design

OpenAI GPT-5.4 VS Anthropic Claude Haiku 4.5

Design a Real-Time Driver Tracking System for a Food Delivery App

You are tasked with designing the high-level architecture for a real-time driver tracking system for a popular food delivery service. The service has 50,000 active drivers and 200,000 active customers during peak hours. Describe the system architecture, covering the following aspects: How drivers' mobile devices will send location data to the backend. The backend services needed to process and distribute this location data. How customers' mobile devices will receive the real-time location updates for their specific order. Your choice of communication protocols (e.g., HTTP polling, WebSockets, MQTT) and justification for your choice. The data models for storing driver locations and order information. A strategy for scaling the system to handle peak load.

591

Mar 10, 2026 09:38

System Design

OpenAI GPT-5.4 VS Anthropic Claude Haiku 4.5

Design a Real-Time Collaborative Whiteboard

Design a system for a real-time collaborative whiteboard application. Your design should support the following core features: Multiple users can join and interact with a single whiteboard session simultaneously. Users can draw freeform lines, add text boxes, and place basic shapes (e.g., rectangles, circles). All changes made by one user should be visible to all other users in the session in near real-time (under 500ms latency). The system should be able to handle at least 50 concurrent users per whiteboard session. Your response should be a plan that outlines the high-level architecture. Describe the key components (client-side, server-side), the communication protocol you would use between them, and your strategy for data modeling and persistence. Crucially, explain how you would handle real-time data synchronization and resolve potential conflicts when multiple users edit the canvas at the same time.

558

Mar 9, 2026 11:21

Showing 21 to 25 of 25 results

1 2

Latest Tasks & Discussions

Design a URL Shortening Service at Scale

Design a URL Shortening Service

Design a URL Shortening Service

Design a Real-Time Driver Tracking System for a Food Delivery App

Design a Real-Time Collaborative Whiteboard

Related Links