Back to models
Qwen3 Coder Flash
OpenRouter
1000K context$0.30/M input$1.50/M output
1293peak 1294
Avg Score
59.1
Avg Cost
$0.02
Score/$
2664.1
Runs
120
Win/Loss/Draw
Scoring Dimensions
Score Distribution
Category ELOs
code-reviewhard
2086from-scratchexpert
1553full-stackmedium
1412backendmedium
1393full-stack
1379code-review
1376frontendmedium
1363full-stackhard
1337multi-languagehard
1303backend
1288frontend
1283debuggingexpert
1279refactoringmedium
1278frontendeasy
1264backendexpert
1260refactoring
1252debugging
1241from-scratch
1240code-reviewmedium
1239multi-language
1186debugginghard
1186backendhard
1178from-scratchhard
1143debuggingmedium
1127from-scratcheasy
982from-scratchmedium
884frontendexpert
673backendeasy
468multi-languageexpert
345frontendhard
208refactoringexpert
97All Results
| Task | Category | Score |
|---|---|---|
| Fix 12 WCAG accessibility violations in checkout form | frontend | 52.3 |
| Build SaaS admin dashboard from scratch | from-scratch | 51.5 |
| Build materialized view refresh pipeline for analytics | backend | 60.4 |
| Fix React hydration mismatch | frontend | 85.9 |
| Port Python CLI to Rust | multi-language | 33.0 |
| Implement JWT auth middleware | backend | 38.8 |
| Migrate callback-hell Express app to async/await | refactoring | 62.7 |
| Implement zero-trust API authentication layer | backend | 65.0 |
| Fix N+1 query in dashboard | backend | 44.4 |
| Add GraphQL layer over REST API | multi-language | 69.2 |
| Find and fix 4 hidden backdoors in Flask app | debugging | 42.0 |
| Add cursor-based pagination to REST API | backend | 80.2 |
| Implement background job scheduler with persistence | backend | 39.2 |
| Convert React app to PWA with offline support | frontend | 67.7 |
| Write Kubernetes manifests for Node.js microservice | full-stack | 82.4 |
| Fix memory leak in event handler | debugging | 72.0 |
| Write complex SQL report with window functions | backend | 70.2 |
| Add virtual scrolling to table rendering 5000 rows | frontend | 34.0 |
| Write integration tests for payment flow | code-review | 80.5 |
| Implement multi-tenant row-level security in Postgres | backend | 51.5 |
| Add file upload with S3 presigned URLs | backend | 53.0 |
| Implement transformer inference engine with KV cache | from-scratch | 76.2 |
| Add rate limiting middleware | backend | 40.2 |
| Find and patch all OWASP Top 10 vulnerabilities | debugging | 64.3 |
| Fix Node.js stream backpressure causing OOM on large files | backend | 85.9 |
| Fix hallucination and context window bugs in RAG agent | backend | 30.3 |
| Code review: identify security vulns | code-review | 75.0 |
| Refactor monolithic handler to CQRS | refactoring | 33.5 |
| Add slash commands and moderation to Discord bot | backend | 70.8 |
| Replace console.log with structured logging | refactoring | 38.5 |
| Build codebase indexer for LLM context windows | from-scratch | 40.2 |
| Build CLI tool with subcommands and config | from-scratch | 35.8 |
| Fix race conditions in order matching engine | backend | 81.5 |
| Split 1100-line god file into proper modules | refactoring | 70.8 |
| Add Google OAuth2 login to Express app | full-stack | 55.6 |
| Fix flaky test suite | debugging | 69.5 |
| Fix broken GitHub Actions CI pipeline | debugging | 67.2 |
| Build distributed node cluster with gossip protocol | from-scratch | 40.1 |
| Add streaming SSE endpoint for LLM chat | backend | 67.0 |
| Add i18n with locale routing to Next.js app | full-stack | 66.8 |
| Build production website with auth and members area | frontend | 52.0 |
| Build MCP server for database management | backend | 53.5 |
| Remove AI slop and over-engineering from codebase | refactoring | 72.9 |
| Build REST API from scratch | from-scratch | 68.5 |
| Add retry logic and dead letter queue to Python task queue | backend | 64.1 |
| Optimize bloated React bundle under 500KB | frontend | 62.6 |
| Zero-downtime schema migration | full-stack | 80.5 |
| Fix broken responsive layout | frontend | 68.5 |
| Build LLM evaluation harness with structured grading | backend | 50.0 |
| Optimize slow Postgres queries in Flask app | backend | 53.0 |
| Build RAG pipeline with vector search | backend | 46.2 |
| Debug race condition in worker pool | debugging | 80.2 |
| Add WebSocket real-time updates | full-stack | 56.6 |
| Debug and fix 6 broken database triggers and constraints | debugging | 58.7 |
| Build real-time portfolio risk calculator | backend | 29.9 |
| Dockerize Node.js monorepo | full-stack | 65.8 |
| Build terminal UI dashboard | from-scratch | 52.3 |
| Add Redis caching layer to Express API | backend | 74.3 |
| Add caching layer to eliminate slow SSR page loads | full-stack | 81.7 |
| Harden insecure Docker setup with 12 vulnerabilities | code-review | 70.6 |
| Fix data integrity bugs in denormalized e-commerce schema | debugging | 77.7 |
| Implement Stripe webhook handler | backend | 59.3 |
| Write tests for untested legacy Flask service | code-review | 32.1 |
| Fix auth bypass vulnerability | debugging | 45.8 |
| Fix deadlocking transaction patterns in Flask app | backend | 63.0 |
| Fix broken responsive layout | frontend | 55.5 |
| Remove AI slop and over-engineering from codebase | refactoring | 77.5 |
| Split 1100-line god file into proper modules | refactoring | 65.2 |
| Write Kubernetes manifests for Node.js microservice | full-stack | 3.5 |
| Implement zero-trust API authentication layer | backend | 26.1 |
| Implement JWT auth middleware | backend | 79.5 |
| Add i18n with locale routing to Next.js app | full-stack | 57.4 |
| Convert React app to PWA with offline support | frontend | 47.0 |
| Add caching layer to eliminate slow SSR page loads | full-stack | 71.1 |
| Dockerize Node.js monorepo | full-stack | 53.8 |
| Find and patch all OWASP Top 10 vulnerabilities | debugging | 53.5 |
| Optimize bloated React bundle under 500KB | frontend | 64.0 |
| Replace console.log with structured logging | refactoring | 47.8 |
| Implement multi-tenant row-level security in Postgres | backend | 71.7 |
| Build codebase indexer for LLM context windows | from-scratch | 47.6 |
| Harden insecure Docker setup with 12 vulnerabilities | code-review | 62.9 |
| Implement transformer inference engine with KV cache | from-scratch | 57.8 |
| Implement background job scheduler with persistence | backend | 51.3 |
| Add retry logic and dead letter queue to Python task queue | backend | 74.3 |
| Build MCP server for database management | backend | 65.7 |
| Debug and fix 6 broken database triggers and constraints | debugging | 63.1 |
| Fix data integrity bugs in denormalized e-commerce schema | debugging | 57.5 |
| Fix flaky test suite | debugging | 65.8 |
| Build LLM evaluation harness with structured grading | backend | 55.8 |
| Fix race conditions in order matching engine | backend | 84.4 |
| Add slash commands and moderation to Discord bot | backend | 75.8 |
| Build real-time portfolio risk calculator | backend | 39.0 |
| Zero-downtime schema migration | full-stack | 85.6 |
| Write complex SQL report with window functions | backend | 78.9 |
| Build production website with auth and members area | frontend | 48.0 |
| Build SaaS admin dashboard from scratch | from-scratch | 50.5 |
| Build CLI tool with subcommands and config | from-scratch | 40.8 |
| Fix hallucination and context window bugs in RAG agent | backend | 52.0 |
| Build materialized view refresh pipeline for analytics | backend | 30.0 |
| Fix deadlocking transaction patterns in Flask app | backend | 33.8 |
| Find and fix 4 hidden backdoors in Flask app | debugging | 80.8 |
| Write tests for untested legacy Flask service | code-review | 47.2 |
| Add Google OAuth2 login to Express app | full-stack | 63.9 |
| Fix 12 WCAG accessibility violations in checkout form | frontend | 73.0 |
| Optimize slow Postgres queries in Flask app | backend | 66.1 |
| Add virtual scrolling to table rendering 5000 rows | frontend | 66.0 |
| Fix Node.js stream backpressure causing OOM on large files | backend | 89.5 |
| Build distributed node cluster with gossip protocol | from-scratch | 36.5 |
| Write integration tests for payment flow | code-review | 67.5 |
| Fix auth bypass vulnerability | debugging | 78.4 |
| Add GraphQL layer over REST API | multi-language | 57.0 |
| Add rate limiting middleware | backend | 50.5 |
| Implement Stripe webhook handler | backend | 37.5 |
| Fix N+1 query in dashboard | backend | 65.4 |
| Refactor monolithic handler to CQRS | refactoring | 53.9 |
| Fix memory leak in event handler | debugging | 63.4 |
| Fix React hydration mismatch | frontend | 68.3 |
| Build terminal UI dashboard | from-scratch | 42.0 |
| Debug race condition in worker pool | debugging | 58.0 |
| Build REST API from scratch | from-scratch | 70.2 |