Back to models
Qwen3 Coder Plus
OpenRouter
1000K context$1.00/M input$5.00/M output
1351peak 1367
Avg Score
64.6
Avg Cost
$0.04
Score/$
1523.4
Runs
65
Win/Loss/Draw
Scoring Dimensions
Score Distribution
Category ELOs
from-scratchexpert
1673debuggingexpert
1545debugginghard
1473code-reviewhard
1442backendmedium
1430debugging
1429full-stackhard
1414frontendmedium
1388full-stack
1386backend
1369backendhard
1335backendexpert
1335full-stackmedium
1324from-scratch
1322frontendexpert
1319frontend
1315refactoringmedium
1262from-scratcheasy
1249refactoring
1248code-review
1237multi-languagehard
1237from-scratchhard
1230multi-language
1146code-reviewmedium
1140debuggingmedium
1011from-scratchmedium
991frontendhard
886backendeasy
651refactoringexpert
299multi-languageexpert
285frontendeasy
36All Results
| Task | Category | Score |
|---|---|---|
| Build production website with auth and members area | frontend | 63.8 |
| Build terminal UI dashboard | from-scratch | 55.1 |
| Build CLI tool with subcommands and config | from-scratch | 55.1 |
| Zero-downtime schema migration | full-stack | 72.2 |
| Split 1100-line god file into proper modules | refactoring | 61.6 |
| Build REST API from scratch | from-scratch | 74.5 |
| Fix data integrity bugs in denormalized e-commerce schema | debugging | 87.0 |
| Optimize slow Postgres queries in Flask app | backend | 82.6 |
| Add Redis caching layer to Express API | backend | 84.9 |
| Remove AI slop and over-engineering from codebase | refactoring | 66.3 |
| Fix React hydration mismatch | frontend | 74.8 |
| Add virtual scrolling to table rendering 5000 rows | frontend | 76.6 |
| Implement background job scheduler with persistence | backend | 49.9 |
| Replace console.log with structured logging | refactoring | 64.0 |
| Optimize bloated React bundle under 500KB | frontend | 66.1 |
| Fix 12 WCAG accessibility violations in checkout form | frontend | 69.3 |
| Write tests for untested legacy Flask service | code-review | 47.3 |
| Harden insecure Docker setup with 12 vulnerabilities | code-review | 47.3 |
| Fix broken GitHub Actions CI pipeline | debugging | 77.0 |
| Build distributed node cluster with gossip protocol | from-scratch | 43.5 |
| Write integration tests for payment flow | code-review | 71.8 |
| Implement JWT auth middleware | backend | 49.4 |
| Build codebase indexer for LLM context windows | from-scratch | 43.0 |
| Code review: identify security vulns | code-review | 63.0 |
| Write complex SQL report with window functions | backend | 62.6 |
| Fix broken responsive layout | frontend | 44.2 |
| Add slash commands and moderation to Discord bot | backend | 70.5 |
| Fix Node.js stream backpressure causing OOM on large files | backend | 74.0 |
| Build RAG pipeline with vector search | backend | 37.3 |
| Implement transformer inference engine with KV cache | from-scratch | 79.5 |
| Add rate limiting middleware | backend | 45.0 |
| Build materialized view refresh pipeline for analytics | backend | 72.3 |
| Refactor monolithic handler to CQRS | refactoring | 38.5 |
| Implement zero-trust API authentication layer | backend | 67.1 |
| Add file upload with S3 presigned URLs | backend | 75.7 |
| Add Google OAuth2 login to Express app | full-stack | 80.0 |
| Add retry logic and dead letter queue to Python task queue | backend | 77.0 |
| Debug race condition in worker pool | debugging | 86.4 |
| Build MCP server for database management | backend | 80.2 |
| Find and fix 4 hidden backdoors in Flask app | debugging | 87.7 |
| Implement Stripe webhook handler | backend | 74.9 |
| Fix auth bypass vulnerability | debugging | 73.2 |
| Dockerize Node.js monorepo | full-stack | 71.0 |
| Add GraphQL layer over REST API | multi-language | 70.1 |
| Fix hallucination and context window bugs in RAG agent | backend | 27.4 |
| Write Kubernetes manifests for Node.js microservice | full-stack | 75.5 |
| Convert React app to PWA with offline support | frontend | 69.3 |
| Build LLM evaluation harness with structured grading | backend | 70.9 |
| Add caching layer to eliminate slow SSR page loads | full-stack | 80.8 |
| Build real-time portfolio risk calculator | backend | 37.2 |
| Port Python CLI to Rust | multi-language | 32.8 |
| Add i18n with locale routing to Next.js app | full-stack | 61.9 |
| Migrate callback-hell Express app to async/await | refactoring | 60.7 |
| Fix deadlocking transaction patterns in Flask app | backend | 68.2 |
| Find and patch all OWASP Top 10 vulnerabilities | debugging | 63.9 |
| Fix flaky test suite | debugging | 22.8 |
| Build SaaS admin dashboard from scratch | from-scratch | 51.8 |
| Fix N+1 query in dashboard | backend | 37.0 |
| Implement multi-tenant row-level security in Postgres | backend | 61.6 |
| Add streaming SSE endpoint for LLM chat | backend | 71.7 |
| Debug and fix 6 broken database triggers and constraints | debugging | 83.8 |
| Add cursor-based pagination to REST API | backend | 76.9 |
| Fix race conditions in order matching engine | backend | 79.3 |
| Fix memory leak in event handler | debugging | 78.8 |
| Add WebSocket real-time updates | full-stack | 70.5 |