Back to models
Qwen3 Coder
OpenRouter
262K context$0.22/M input$1.00/M output
1360peak 1388
Avg Score
64.7
Avg Cost
$0.03
Score/$
2563.6
Runs
65
Win/Loss/Draw
Scoring Dimensions
Score Distribution
Category ELOs
refactoringexpert
1990multi-languagehard
1601debugginghard
1584debuggingmedium
1560debugging
1470backendmedium
1457full-stackmedium
1441frontendhard
1407frontendmedium
1389frontend
1358full-stack
1357backend
1357backendhard
1343frontendexpert
1337refactoring
1334multi-language
1305debuggingexpert
1289from-scratchhard
1288from-scratch
1282from-scratchexpert
1281full-stackhard
1271refactoringmedium
1192code-review
1184code-reviewmedium
1183backendexpert
1171from-scratcheasy
1150code-reviewhard
895from-scratchmedium
810backendeasy
764frontendeasy
722multi-languageexpert
509All Results
| Task | Category | Score |
|---|---|---|
| Write tests for untested legacy Flask service | code-review | 49.0 |
| Add file upload with S3 presigned URLs | backend | 9.8 |
| Build real-time portfolio risk calculator | backend | 49.8 |
| Debug and fix 6 broken database triggers and constraints | debugging | 49.6 |
| Debug race condition in worker pool | debugging | 89.2 |
| Fix 12 WCAG accessibility violations in checkout form | frontend | 75.3 |
| Migrate callback-hell Express app to async/await | refactoring | 64.1 |
| Add cursor-based pagination to REST API | backend | 71.2 |
| Fix Node.js stream backpressure causing OOM on large files | backend | 88.3 |
| Add streaming SSE endpoint for LLM chat | backend | 81.8 |
| Add i18n with locale routing to Next.js app | full-stack | 62.5 |
| Fix broken GitHub Actions CI pipeline | debugging | 84.8 |
| Fix deadlocking transaction patterns in Flask app | backend | 72.3 |
| Fix hallucination and context window bugs in RAG agent | backend | 44.8 |
| Add rate limiting middleware | backend | 40.0 |
| Port Python CLI to Rust | multi-language | 39.0 |
| Build SaaS admin dashboard from scratch | from-scratch | 57.8 |
| Add slash commands and moderation to Discord bot | backend | 79.5 |
| Build production website with auth and members area | frontend | 66.1 |
| Replace console.log with structured logging | refactoring | 45.0 |
| Add virtual scrolling to table rendering 5000 rows | frontend | 71.5 |
| Build materialized view refresh pipeline for analytics | backend | 73.3 |
| Implement multi-tenant row-level security in Postgres | backend | 59.1 |
| Refactor monolithic handler to CQRS | refactoring | 79.3 |
| Build RAG pipeline with vector search | backend | 47.4 |
| Implement Stripe webhook handler | backend | 82.8 |
| Build terminal UI dashboard | from-scratch | 45.1 |
| Fix React hydration mismatch | frontend | 85.3 |
| Fix data integrity bugs in denormalized e-commerce schema | debugging | 81.0 |
| Implement background job scheduler with persistence | backend | 37.3 |
| Build CLI tool with subcommands and config | from-scratch | 61.4 |
| Split 1100-line god file into proper modules | refactoring | 67.1 |
| Optimize slow Postgres queries in Flask app | backend | 62.4 |
| Find and fix 4 hidden backdoors in Flask app | debugging | 91.3 |
| Fix flaky test suite | debugging | 86.0 |
| Fix auth bypass vulnerability | debugging | 82.8 |
| Add retry logic and dead letter queue to Python task queue | backend | 79.4 |
| Add GraphQL layer over REST API | multi-language | 78.1 |
| Implement zero-trust API authentication layer | backend | 61.2 |
| Fix broken responsive layout | frontend | 64.0 |
| Fix N+1 query in dashboard | backend | 54.4 |
| Build LLM evaluation harness with structured grading | backend | 45.4 |
| Convert React app to PWA with offline support | frontend | 72.4 |
| Harden insecure Docker setup with 12 vulnerabilities | code-review | 47.1 |
| Find and patch all OWASP Top 10 vulnerabilities | debugging | 66.2 |
| Add Redis caching layer to Express API | backend | 81.3 |
| Write integration tests for payment flow | code-review | 64.2 |
| Add Google OAuth2 login to Express app | full-stack | 82.0 |
| Fix memory leak in event handler | debugging | 70.9 |
| Implement transformer inference engine with KV cache | from-scratch | 74.2 |
| Implement JWT auth middleware | backend | 44.3 |
| Write Kubernetes manifests for Node.js microservice | full-stack | 85.0 |
| Code review: identify security vulns | code-review | 75.0 |
| Dockerize Node.js monorepo | full-stack | 70.8 |
| Write complex SQL report with window functions | backend | 62.4 |
| Remove AI slop and over-engineering from codebase | refactoring | 80.0 |
| Build MCP server for database management | backend | 74.5 |
| Add WebSocket real-time updates | full-stack | 59.5 |
| Build codebase indexer for LLM context windows | from-scratch | 42.4 |
| Zero-downtime schema migration | full-stack | 53.9 |
| Build REST API from scratch | from-scratch | 72.5 |
| Add caching layer to eliminate slow SSR page loads | full-stack | 83.5 |
| Build distributed node cluster with gossip protocol | from-scratch | 35.5 |
| Optimize bloated React bundle under 500KB | frontend | 33.8 |
| Fix race conditions in order matching engine | backend | 59.9 |