Back to models
Qwen3.5 397b A17b
OpenRouter
262K context$0.60/M input$3.60/M output
1549peak 1558
Avg Score
68.0
Avg Cost
$0.12
Score/$
571.7
Runs
123
Win/Loss/Draw
Scoring Dimensions
Score Distribution
Category ELOs
multi-languagehard
2101backendeasy
1923refactoringexpert
1912from-scratchmedium
1896code-reviewhard
1842frontendexpert
1743frontendhard
1722debuggingmedium
1703full-stackhard
1640full-stackmedium
1636backendexpert
1626full-stack
1619backendhard
1588backend
1584debugginghard
1584frontendmedium
1581frontend
1574refactoring
1563backendmedium
1552from-scratchhard
1542debugging
1535refactoringmedium
1509code-review
1480multi-language
1477from-scratch
1476debuggingexpert
1448frontendeasy
1433code-reviewmedium
1414from-scratcheasy
1413multi-languageexpert
1147from-scratchexpert
0All Results
| Task | Category | Score |
|---|---|---|
| Fix data integrity bugs in denormalized e-commerce schema | debugging | 49.0 |
| Split 1100-line god file into proper modules | refactoring | 42.3 |
| Build REST API from scratch | from-scratch | 74.5 |
| Refactor monolithic handler to CQRS | refactoring | 38.3 |
| Build materialized view refresh pipeline for analytics | backend | 72.8 |
| Add cursor-based pagination to REST API | backend | 80.5 |
| Implement JWT auth middleware | backend | 55.1 |
| Build SaaS admin dashboard from scratch | from-scratch | 42.8 |
| Fix memory leak in event handler | debugging | 80.1 |
| Build codebase indexer for LLM context windows | from-scratch | 34.5 |
| Add retry logic and dead letter queue to Python task queue | backend | 83.6 |
| Debug race condition in worker pool | debugging | 85.3 |
| Fix N+1 query in dashboard | backend | 53.4 |
| Optimize slow Postgres queries in Flask app | backend | 85.2 |
| Implement Stripe webhook handler | backend | 83.6 |
| Replace console.log with structured logging | refactoring | 53.4 |
| Write tests for untested legacy Flask service | code-review | 50.7 |
| Convert React app to PWA with offline support | frontend | 77.5 |
| Fix 12 WCAG accessibility violations in checkout form | frontend | 62.6 |
| Implement background job scheduler with persistence | backend | 54.8 |
| Build CLI tool with subcommands and config | from-scratch | 65.3 |
| Add file upload with S3 presigned URLs | backend | 65.5 |
| Write integration tests for payment flow | code-review | 80.5 |
| Fix hallucination and context window bugs in RAG agent | backend | 51.3 |
| Add rate limiting middleware | backend | 44.6 |
| Implement multi-tenant row-level security in Postgres | backend | 43.9 |
| Add Redis caching layer to Express API | backend | 81.6 |
| Add Google OAuth2 login to Express app | full-stack | 78.3 |
| Code review: identify security vulns | code-review | 34.0 |
| Add slash commands and moderation to Discord bot | backend | 69.6 |
| Zero-downtime schema migration | full-stack | 74.2 |
| Implement zero-trust API authentication layer | backend | 72.1 |
| Fix React hydration mismatch | frontend | 80.6 |
| Find and patch all OWASP Top 10 vulnerabilities | debugging | 65.9 |
| Add GraphQL layer over REST API | multi-language | 84.0 |
| Remove AI slop and over-engineering from codebase | refactoring | 74.8 |
| Build LLM evaluation harness with structured grading | backend | 76.3 |
| Find and fix 4 hidden backdoors in Flask app | debugging | 76.3 |
| Fix race conditions in order matching engine | backend | 75.7 |
| Write Kubernetes manifests for Node.js microservice | full-stack | 85.5 |
| Fix broken responsive layout | frontend | 62.8 |
| Harden insecure Docker setup with 12 vulnerabilities | code-review | 79.0 |
| Build production website with auth and members area | frontend | 63.5 |
| Fix broken GitHub Actions CI pipeline | debugging | 84.7 |
| Add virtual scrolling to table rendering 5000 rows | frontend | 51.5 |
| Fix deadlocking transaction patterns in Flask app | backend | 77.4 |
| Dockerize Node.js monorepo | full-stack | 75.7 |
| Build real-time portfolio risk calculator | backend | 54.5 |
| Migrate callback-hell Express app to async/await | refactoring | 72.9 |
| Port Python CLI to Rust | multi-language | 33.6 |
| Optimize bloated React bundle under 500KB | frontend | 70.8 |
| Fix auth bypass vulnerability | debugging | 89.3 |
| Fix Node.js stream backpressure causing OOM on large files | backend | 87.0 |
| Debug and fix 6 broken database triggers and constraints | debugging | 60.7 |
| Add caching layer to eliminate slow SSR page loads | full-stack | 81.0 |
| Add i18n with locale routing to Next.js app | full-stack | 72.7 |
| Build RAG pipeline with vector search | backend | 40.0 |
| Add WebSocket real-time updates | full-stack | 82.4 |
| Build distributed node cluster with gossip protocol | from-scratch | 31.9 |
| Build MCP server for database management | backend | 82.0 |
| Write complex SQL report with window functions | backend | 61.0 |
| Implement transformer inference engine with KV cache | from-scratch | 34.8 |
| Add streaming SSE endpoint for LLM chat | backend | 77.8 |
| Build terminal UI dashboard | from-scratch | 40.5 |
| Fix flaky test suite | debugging | 81.9 |
| Implement zero-trust API authentication layer | backend | 66.1 |
| Build codebase indexer for LLM context windows | from-scratch | 55.0 |
| Fix broken responsive layout | frontend | 72.0 |
| Optimize bloated React bundle under 500KB | frontend | 73.6 |
| Add caching layer to eliminate slow SSR page loads | full-stack | 84.8 |
| Convert React app to PWA with offline support | frontend | 71.3 |
| Add streaming SSE endpoint for LLM chat | backend | 81.8 |
| Remove AI slop and over-engineering from codebase | refactoring | 81.3 |
| Implement multi-tenant row-level security in Postgres | backend | 74.5 |
| Dockerize Node.js monorepo | full-stack | 75.6 |
| Replace console.log with structured logging | refactoring | 45.6 |
| Find and patch all OWASP Top 10 vulnerabilities | debugging | 68.3 |
| Implement JWT auth middleware | backend | 82.4 |
| Split 1100-line god file into proper modules | refactoring | 72.5 |
| Add i18n with locale routing to Next.js app | full-stack | 65.8 |
| Write Kubernetes manifests for Node.js microservice | full-stack | 85.2 |
| Harden insecure Docker setup with 12 vulnerabilities | code-review | 73.8 |
| Build production website with auth and members area | frontend | 67.7 |
| Build SaaS admin dashboard from scratch | from-scratch | 69.8 |
| Build MCP server for database management | backend | 80.0 |
| Build CLI tool with subcommands and config | from-scratch | 46.0 |
| Implement transformer inference engine with KV cache | from-scratch | 42.8 |
| Implement background job scheduler with persistence | backend | 53.4 |
| Fix hallucination and context window bugs in RAG agent | backend | 70.4 |
| Build LLM evaluation harness with structured grading | backend | 63.1 |
| Build real-time portfolio risk calculator | backend | 64.7 |
| Fix race conditions in order matching engine | backend | 87.1 |
| Build materialized view refresh pipeline for analytics | backend | 71.2 |
| Fix data integrity bugs in denormalized e-commerce schema | debugging | 68.5 |
| Fix deadlocking transaction patterns in Flask app | backend | 68.4 |
| Write complex SQL report with window functions | backend | 81.2 |
| Debug and fix 6 broken database triggers and constraints | debugging | 80.5 |
| Write tests for untested legacy Flask service | code-review | 56.1 |
| Find and fix 4 hidden backdoors in Flask app | debugging | 93.3 |
| Add Redis caching layer to Express API | backend | 69.5 |
| Optimize slow Postgres queries in Flask app | backend | 82.8 |
| Add slash commands and moderation to Discord bot | backend | 60.0 |
| Add retry logic and dead letter queue to Python task queue | backend | 78.7 |
| Fix 12 WCAG accessibility violations in checkout form | frontend | 84.1 |
| Fix Node.js stream backpressure causing OOM on large files | backend | 77.5 |
| Add virtual scrolling to table rendering 5000 rows | frontend | 74.0 |
| Write integration tests for payment flow | code-review | 39.6 |
| Build distributed node cluster with gossip protocol | from-scratch | 41.3 |
| Fix auth bypass vulnerability | debugging | 93.7 |
| Add GraphQL layer over REST API | multi-language | 67.2 |
| Add rate limiting middleware | backend | 81.8 |
| Zero-downtime schema migration | full-stack | 63.1 |
| Fix flaky test suite | debugging | 83.5 |
| Build terminal UI dashboard | from-scratch | 66.7 |
| Implement Stripe webhook handler | backend | 61.0 |
| Refactor monolithic handler to CQRS | refactoring | 71.2 |
| Add cursor-based pagination to REST API | backend | 52.5 |
| Code review: identify security vulns | code-review | 59.3 |
| Fix N+1 query in dashboard | backend | 74.5 |
| Fix memory leak in event handler | debugging | 58.5 |
| Debug race condition in worker pool | debugging | 85.7 |
| Fix React hydration mismatch | frontend | 76.1 |
| Build REST API from scratch | from-scratch | 81.1 |