Software Engineering Skill Leaderboard

Design codebases and review implementations.

Plan engineering work and coordinate parallel agents.

Clarify requirements and keep code changes focused.

Audit repository quality and track technical debt.

Map codebases into navigable knowledge graphs.

Plan, review, test, and ship software with specialist agents.

Reduce agent verbosity and context consumption.

Specify, build, verify, and ship software incrementally.

Build company websites with cohesive visual design.

Audit UX and refine frontend design.

Explore codebases and knowledge through interactive graphs.

Automate business workflows across connected apps.

Design interfaces and refine interaction animations.

Enforce design tokens and accessibility standards.

Prototype, test, and develop playable games.

Optimize React applications and Vercel deployments.

Run engineering, product, marketing, and business workflows.

Build applications, process documents, and automate Codex workflows.

Build and operate applications with Google technologies.

Build and optimize animations with GSAP.

Automate app integrations and productivity workflows in Codex.

Create films from stories using code-driven visual styles.

Redesign generic interfaces with a distinct visual direction.

Train, evaluate, and research machine learning models.

Build applications and create documents and multimedia.

Develop, test, and operate full-stack applications.

Refine interface layout, typography, color, and accessibility.

Create datasets and train and evaluate models on Hugging Face.

Improve interface design, accessibility, and motion performance.

Turn system descriptions into editable draw.io architecture diagrams.

Create and test mods for PC games.

Recreate app functionality with original code and branding.

Coordinate persistent teams of coding agents.

Design interfaces in Stitch and turn them into applications.

Reverse-engineer Android apps and extract their APIs.

Structure brainstorming and agent development workflows.

Plan, design, debug, and review software changes.

Optimize prompts and code through evaluation-driven search.

Create and render videos with Remotion.

Build 2D and 3D browser games with melonJS.

Structure coding workflows with testing, memory, and verification.

Build, modernize, and troubleshoot .NET applications.

Develop Vue applications and maintain JavaScript tooling.

Research, design, and implement software changes.

Research, repurpose, and archive content across creator workflows.

Build scroll-driven websites with coordinated motion and layout.

Explore and critique ideas through parallel reasoning.

Build applications with Gemini APIs.

Plan, implement, and verify software changes.

Build and optimize interactive Three.js scenes.