Back to models
Qwen3.5 122b A10b
OpenRouter
262K context$0.40/M input$3.20/M output
1564peak 1574
Avg Score
69.2
Avg Cost
$0.38
Score/$
182.8
Runs
124
Win/Loss/Draw
Scoring Dimensions
Score Distribution
Category ELOs
multi-languagehard
1979code-reviewmedium
1951frontendhard
1887refactoringexpert
1822frontendexpert
1764code-review
1758from-scratchexpert
1733debuggingexpert
1720backendexpert
1684backendhard
1624backendeasy
1620full-stackhard
1604debuggingmedium
1603debugging
1597backend
1594refactoring
1592multi-language
1574debugginghard
1561refactoringmedium
1549backendmedium
1548frontend
1535full-stack
1526from-scratchmedium
1489frontendeasy
1486frontendmedium
1474full-stackmedium
1473code-reviewhard
1422from-scratch
1406from-scratchhard
1383from-scratcheasy
1373multi-languageexpert
1168All Results
| Task | Category | Score |
|---|---|---|
| Build LLM evaluation harness with structured grading | backend | 67.3 |
| Fix React hydration mismatch | frontend | 79.5 |
| Build SaaS admin dashboard from scratch | from-scratch | 54.2 |
| Add i18n with locale routing to Next.js app | full-stack | 70.0 |
| Build distributed node cluster with gossip protocol | from-scratch | 30.6 |
| Add rate limiting middleware | backend | 35.3 |
| Add streaming SSE endpoint for LLM chat | backend | 82.5 |
| Add GraphQL layer over REST API | multi-language | 80.5 |
| Add caching layer to eliminate slow SSR page loads | full-stack | 77.3 |
| Implement multi-tenant row-level security in Postgres | backend | 34.6 |
| Add slash commands and moderation to Discord bot | backend | 60.6 |
| Build REST API from scratch | from-scratch | 74.3 |
| Port Python CLI to Rust | multi-language | 33.8 |
| Add virtual scrolling to table rendering 5000 rows | frontend | 82.8 |
| Code review: identify security vulns | code-review | 37.2 |
| Build codebase indexer for LLM context windows | from-scratch | 37.3 |
| Fix Node.js stream backpressure causing OOM on large files | backend | 88.3 |
| Dockerize Node.js monorepo | full-stack | 67.1 |
| Fix broken GitHub Actions CI pipeline | debugging | 85.9 |
| Optimize slow Postgres queries in Flask app | backend | 71.1 |
| Convert React app to PWA with offline support | frontend | 71.6 |
| Replace console.log with structured logging | refactoring | 54.5 |
| Build MCP server for database management | backend | 82.4 |
| Implement Stripe webhook handler | backend | 61.5 |
| Refactor monolithic handler to CQRS | refactoring | 49.7 |
| Add Redis caching layer to Express API | backend | 84.2 |
| Fix broken responsive layout | frontend | 70.0 |
| Implement JWT auth middleware | backend | 47.9 |
| Add retry logic and dead letter queue to Python task queue | backend | 67.2 |
| Implement transformer inference engine with KV cache | from-scratch | 80.7 |
| Implement background job scheduler with persistence | backend | 50.0 |
| Find and patch all OWASP Top 10 vulnerabilities | debugging | 65.5 |
| Add cursor-based pagination to REST API | backend | 82.8 |
| Optimize bloated React bundle under 500KB | frontend | 64.5 |
| Implement zero-trust API authentication layer | backend | 71.3 |
| Fix deadlocking transaction patterns in Flask app | backend | 57.8 |
| Zero-downtime schema migration | full-stack | 82.9 |
| Build real-time portfolio risk calculator | backend | 55.6 |
| Fix auth bypass vulnerability | debugging | 87.0 |
| Find and fix 4 hidden backdoors in Flask app | debugging | 86.2 |
| Write integration tests for payment flow | code-review | 75.5 |
| Fix flaky test suite | debugging | 70.5 |
| Fix race conditions in order matching engine | backend | 86.5 |
| Split 1100-line god file into proper modules | refactoring | 71.2 |
| Harden insecure Docker setup with 12 vulnerabilities | code-review | 81.0 |
| Debug and fix 6 broken database triggers and constraints | debugging | 90.9 |
| Remove AI slop and over-engineering from codebase | refactoring | 87.5 |
| Build RAG pipeline with vector search | backend | 48.5 |
| Fix N+1 query in dashboard | backend | 52.4 |
| Add Google OAuth2 login to Express app | full-stack | 78.3 |
| Migrate callback-hell Express app to async/await | refactoring | 63.5 |
| Build terminal UI dashboard | from-scratch | 49.1 |
| Fix 12 WCAG accessibility violations in checkout form | frontend | 79.0 |
| Fix data integrity bugs in denormalized e-commerce schema | debugging | 82.4 |
| Write complex SQL report with window functions | backend | 75.0 |
| Add WebSocket real-time updates | full-stack | 67.6 |
| Debug race condition in worker pool | debugging | 88.8 |
| Fix hallucination and context window bugs in RAG agent | backend | 48.3 |
| Add file upload with S3 presigned URLs | backend | 82.0 |
| Write tests for untested legacy Flask service | code-review | 56.6 |
| Fix memory leak in event handler | debugging | 80.3 |
| Build CLI tool with subcommands and config | from-scratch | 42.6 |
| Build production website with auth and members area | frontend | 62.5 |
| Build materialized view refresh pipeline for analytics | backend | 71.6 |
| Write Kubernetes manifests for Node.js microservice | full-stack | 85.0 |
| Port Python CLI to Rust | multi-language | 54.9 |
| Migrate callback-hell Express app to async/await | refactoring | 79.7 |
| Add GraphQL layer over REST API | multi-language | 75.5 |
| Add WebSocket real-time updates | full-stack | 71.5 |
| Fix 12 WCAG accessibility violations in checkout form | frontend | 86.1 |
| Code review: identify security vulns | code-review | 90.9 |
| Add i18n with locale routing to Next.js app | full-stack | 66.9 |
| Optimize bloated React bundle under 500KB | frontend | 69.0 |
| Dockerize Node.js monorepo | full-stack | 67.2 |
| Write Kubernetes manifests for Node.js microservice | full-stack | 88.5 |
| Find and patch all OWASP Top 10 vulnerabilities | debugging | 73.2 |
| Fix broken responsive layout | frontend | 72.3 |
| Split 1100-line god file into proper modules | refactoring | 68.6 |
| Add file upload with S3 presigned URLs | backend | 70.5 |
| Convert React app to PWA with offline support | frontend | 50.8 |
| Implement zero-trust API authentication layer | backend | 75.8 |
| Remove AI slop and over-engineering from codebase | refactoring | 76.5 |
| Build codebase indexer for LLM context windows | from-scratch | 41.9 |
| Harden insecure Docker setup with 12 vulnerabilities | code-review | 77.3 |
| Replace console.log with structured logging | refactoring | 53.7 |
| Implement JWT auth middleware | backend | 79.8 |
| Implement multi-tenant row-level security in Postgres | backend | 64.5 |
| Add caching layer to eliminate slow SSR page loads | full-stack | 74.3 |
| Write complex SQL report with window functions | backend | 89.3 |
| Write integration tests for payment flow | code-review | 33.5 |
| Build real-time portfolio risk calculator | backend | 74.8 |
| Fix race conditions in order matching engine | backend | 84.5 |
| Build CLI tool with subcommands and config | from-scratch | 37.6 |
| Build SaaS admin dashboard from scratch | from-scratch | 45.1 |
| Build distributed node cluster with gossip protocol | from-scratch | 53.2 |
| Implement background job scheduler with persistence | backend | 42.3 |
| Fix N+1 query in dashboard | backend | 67.2 |
| Debug and fix 6 broken database triggers and constraints | debugging | 89.3 |
| Zero-downtime schema migration | full-stack | 79.5 |
| Add retry logic and dead letter queue to Python task queue | backend | 73.1 |
| Build MCP server for database management | backend | 74.3 |
| Implement transformer inference engine with KV cache | from-scratch | 74.0 |
| Fix data integrity bugs in denormalized e-commerce schema | debugging | 88.0 |
| Write tests for untested legacy Flask service | code-review | 84.8 |
| Fix Node.js stream backpressure causing OOM on large files | backend | 74.2 |
| Add Google OAuth2 login to Express app | full-stack | 68.8 |
| Add virtual scrolling to table rendering 5000 rows | frontend | 76.1 |
| Add rate limiting middleware | backend | 76.3 |
| Build terminal UI dashboard | from-scratch | 60.1 |
| Fix React hydration mismatch | frontend | 68.9 |
| Fix memory leak in event handler | debugging | 66.2 |
| Build REST API from scratch | from-scratch | 80.0 |
| Build LLM evaluation harness with structured grading | backend | 73.6 |
| Fix hallucination and context window bugs in RAG agent | backend | 76.0 |
| Build materialized view refresh pipeline for analytics | backend | 71.1 |
| Optimize slow Postgres queries in Flask app | backend | 78.5 |
| Build production website with auth and members area | frontend | 61.0 |
| Find and fix 4 hidden backdoors in Flask app | debugging | 87.0 |
| Add slash commands and moderation to Discord bot | backend | 73.0 |
| Build RAG pipeline with vector search | backend | 68.5 |
| Fix deadlocking transaction patterns in Flask app | backend | 89.7 |
| Fix flaky test suite | debugging | 74.5 |
| Refactor monolithic handler to CQRS | refactoring | 69.1 |
| Debug race condition in worker pool | debugging | 67.0 |