Back to models
Qwen3.6 Plus
OpenRouter
1000K context$0.33/M input$1.95/M output
1564peak 1627
Avg Score
77.8
Avg Cost
$0.41
Score/$
191.3
Runs
70
Win/Loss/Draw
Scoring Dimensions
Score Distribution
Category ELOs
refactoringexpert
2394frontendexpert
2215multi-languagehard
1973backendeasy
1872debuggingmedium
1789from-scratchhard
1743code-reviewmedium
1725backendexpert
1720frontendhard
1700backendhard
1659from-scratchmedium
1659code-review
1629backend
1610from-scratch
1572debugging
1557backendmedium
1551from-scratchexpert
1548debuggingexpert
1537debugginghard
1522full-stackmedium
1522refactoring
1508frontend
1506multi-language
1506full-stack
1504full-stackhard
1487frontendmedium
1464refactoringmedium
1387frontendmaster
1368code-reviewhard
1346backendmaster
1239frontendeasy
1197from-scratcheasy
1185multi-languageexpert
886All Results
| Task | Category | Score |
|---|---|---|
| Add file upload with S3 presigned URLs | backend | 62.1 |
| Implement JWT auth middleware | backend | 79.9 |
| Migrate Express monolith to modular architecture | backend | 33.1 |
| Build interactive data visualization dashboard | frontend | 49.9 |
| Optimize bloated React bundle under 500KB | frontend | 81.0 |
| Build 3D browser game with physics and multiplayer sync | frontend | 74.5 |
| Add streaming SSE endpoint for LLM chat | backend | 72.8 |
| Fix memory leak in event handler | debugging | 80.0 |
| Build multi-tool LLM agent runtime | backend | 81.0 |
| Fix and extend Chrome browser extension | frontend | 73.0 |
| Convert React app to PWA with offline support | frontend | 78.8 |
| Build MCP server for database management | backend | 82.1 |
| Replace console.log with structured logging | refactoring | 43.7 |
| Build SaaS admin dashboard from scratch | from-scratch | 72.9 |
| Harden insecure Docker setup with 12 vulnerabilities | code-review | 89.3 |
| Migrate callback-hell Express app to async/await | refactoring | 87.5 |
| Build RAG pipeline with vector search | backend | 70.4 |
| Fix hallucination and context window bugs in RAG agent | backend | 81.2 |
| Fix Node.js stream backpressure causing OOM on large files | backend | 88.7 |
| Build distributed node cluster with gossip protocol | from-scratch | 79.5 |
| Build LLM evaluation harness with structured grading | backend | 83.8 |
| Write complex SQL report with window functions | backend | 88.3 |
| Build terminal UI dashboard | from-scratch | 69.4 |
| Implement zero-trust API authentication layer | backend | 76.1 |
| Build CLI tool with subcommands and config | from-scratch | 78.8 |
| Add cursor-based pagination to REST API | backend | 82.5 |
| Build materialized view refresh pipeline for analytics | backend | 76.7 |
| Implement multi-tenant row-level security in Postgres | backend | 82.8 |
| Implement transformer inference engine with KV cache | from-scratch | 78.0 |
| Add Redis caching layer to Express API | backend | 81.6 |
| Implement background job scheduler with persistence | backend | 71.2 |
| Fix broken responsive layout | frontend | 70.5 |
| Find and patch all OWASP Top 10 vulnerabilities | debugging | 71.9 |
| Write Kubernetes manifests for Node.js microservice | full-stack | 83.4 |
| Fix broken GitHub Actions CI pipeline | debugging | 90.9 |
| Fix race conditions in order matching engine | backend | 84.4 |
| Add caching layer to eliminate slow SSR page loads | full-stack | 83.7 |
| Fix deadlocking transaction patterns in Flask app | backend | 86.8 |
| Debug race condition in worker pool | debugging | 87.8 |
| Build production website with auth and members area | frontend | 80.8 |
| Fix 12 WCAG accessibility violations in checkout form | frontend | 84.4 |
| Split 1100-line god file into proper modules | refactoring | 76.8 |
| Write integration tests for payment flow | code-review | 71.8 |
| Add retry logic and dead letter queue to Python task queue | backend | 84.5 |
| Add slash commands and moderation to Discord bot | backend | 81.7 |
| Remove AI slop and over-engineering from codebase | refactoring | 76.7 |
| Debug and fix 6 broken database triggers and constraints | debugging | 87.0 |
| Build real-time portfolio risk calculator | backend | 79.5 |
| Build codebase indexer for LLM context windows | from-scratch | 72.5 |
| Add Google OAuth2 login to Express app | full-stack | 61.4 |
| Write tests for untested legacy Flask service | code-review | 87.3 |
| Add GraphQL layer over REST API | multi-language | 84.8 |
| Build REST API from scratch | from-scratch | 78.7 |
| Add virtual scrolling to table rendering 5000 rows | frontend | 74.0 |
| Optimize slow Postgres queries in Flask app | backend | 87.3 |
| Port Python CLI to Rust | multi-language | 45.2 |
| Fix data integrity bugs in denormalized e-commerce schema | debugging | 81.6 |
| Add i18n with locale routing to Next.js app | full-stack | 77.0 |
| Refactor monolithic handler to CQRS | refactoring | 85.8 |
| Code review: identify security vulns | code-review | 81.1 |
| Add WebSocket real-time updates | full-stack | 84.4 |
| Fix N+1 query in dashboard | backend | 79.0 |
| Fix auth bypass vulnerability | debugging | 85.0 |
| Fix flaky test suite | debugging | 91.7 |
| Find and fix 4 hidden backdoors in Flask app | debugging | 89.1 |
| Add rate limiting middleware | backend | 82.3 |
| Zero-downtime schema migration | full-stack | 72.8 |
| Dockerize Node.js monorepo | full-stack | 78.7 |
| Fix React hydration mismatch | frontend | 70.2 |
| Implement Stripe webhook handler | backend | 86.0 |