Back to models
Deepseek R1 0528
OpenRouter
164K context$0.40/M input$1.75/M output
1445peak 1446
Avg Score
64.2
Avg Cost
$0.05
Score/$
1295.9
Runs
103
Win/Loss/Draw
Scoring Dimensions
Score Distribution
Category ELOs
refactoringexpert
1959from-scratchexpert
1956from-scratchmedium
1922backendeasy
1882frontendexpert
1800frontendeasy
1722multi-languageexpert
1635backendexpert
1560full-stackhard
1559debuggingexpert
1519debugginghard
1493full-stack
1475debugging
1472backend
1470backendmedium
1446backendhard
1443multi-languagehard
1440frontend
1439frontendmedium
1416multi-language
1404full-stackmedium
1390debuggingmedium
1384from-scratch
1376frontendhard
1375refactoring
1372from-scratchhard
1316code-reviewmedium
1314from-scratcheasy
1304code-review
1244refactoringmedium
1186code-reviewhard
363All Results
| Task | Category | Score |
|---|---|---|
| Fix 12 WCAG accessibility violations in checkout form | frontend | 68.8 |
| Fix deadlocking transaction patterns in Flask app | backend | 67.6 |
| Build REST API from scratch | from-scratch | 62.8 |
| Build codebase indexer for LLM context windows | from-scratch | 47.1 |
| Write tests for untested legacy Flask service | code-review | 51.2 |
| Zero-downtime schema migration | full-stack | 81.7 |
| Debug race condition in worker pool | debugging | 91.0 |
| Build distributed node cluster with gossip protocol | from-scratch | 39.3 |
| Fix React hydration mismatch | frontend | 82.4 |
| Fix memory leak in event handler | debugging | 83.3 |
| Build production website with auth and members area | frontend | 65.0 |
| Add virtual scrolling to table rendering 5000 rows | frontend | 51.5 |
| Implement multi-tenant row-level security in Postgres | backend | 66.2 |
| Write complex SQL report with window functions | backend | 73.5 |
| Fix broken GitHub Actions CI pipeline | debugging | 75.6 |
| Debug and fix 6 broken database triggers and constraints | debugging | 79.3 |
| Add GraphQL layer over REST API | multi-language | 72.9 |
| Fix Node.js stream backpressure causing OOM on large files | backend | 85.7 |
| Replace console.log with structured logging | refactoring | 55.9 |
| Add caching layer to eliminate slow SSR page loads | full-stack | 87.0 |
| Fix N+1 query in dashboard | backend | 66.1 |
| Add WebSocket real-time updates | full-stack | 74.0 |
| Add i18n with locale routing to Next.js app | full-stack | 66.1 |
| Refactor monolithic handler to CQRS | refactoring | 50.6 |
| Fix auth bypass vulnerability | debugging | 94.1 |
| Find and patch all OWASP Top 10 vulnerabilities | debugging | 68.5 |
| Add streaming SSE endpoint for LLM chat | backend | 81.7 |
| Build real-time portfolio risk calculator | backend | 57.6 |
| Implement zero-trust API authentication layer | backend | 70.7 |
| Implement transformer inference engine with KV cache | from-scratch | 85.8 |
| Migrate callback-hell Express app to async/await | refactoring | 52.0 |
| Add file upload with S3 presigned URLs | backend | 24.6 |
| Fix broken responsive layout | frontend | 73.0 |
| Port Python CLI to Rust | multi-language | 39.5 |
| Build RAG pipeline with vector search | backend | 60.3 |
| Split 1100-line god file into proper modules | refactoring | 62.2 |
| Optimize slow Postgres queries in Flask app | backend | 85.3 |
| Optimize bloated React bundle under 500KB | frontend | 76.8 |
| Code review: identify security vulns | code-review | 45.7 |
| Build MCP server for database management | backend | 71.7 |
| Harden insecure Docker setup with 12 vulnerabilities | code-review | 81.0 |
| Build materialized view refresh pipeline for analytics | backend | 59.5 |
| Fix race conditions in order matching engine | backend | 90.7 |
| Build SaaS admin dashboard from scratch | from-scratch | 38.5 |
| Build LLM evaluation harness with structured grading | backend | 80.5 |
| Add Redis caching layer to Express API | backend | 30.5 |
| Fix hallucination and context window bugs in RAG agent | backend | 63.5 |
| Implement JWT auth middleware | backend | 51.8 |
| Build terminal UI dashboard | from-scratch | 59.4 |
| Write Kubernetes manifests for Node.js microservice | full-stack | 75.6 |
| Convert React app to PWA with offline support | frontend | 10.8 |
| Remove AI slop and over-engineering from codebase | refactoring | 33.3 |
| Build codebase indexer for LLM context windows | from-scratch | 24.5 |
| Find and patch all OWASP Top 10 vulnerabilities | debugging | 72.0 |
| Dockerize Node.js monorepo | full-stack | 64.0 |
| Add i18n with locale routing to Next.js app | full-stack | 62.6 |
| Optimize bloated React bundle under 500KB | frontend | 57.0 |
| Replace console.log with structured logging | refactoring | 48.4 |
| Implement JWT auth middleware | backend | 80.3 |
| Split 1100-line god file into proper modules | refactoring | 63.7 |
| Fix broken responsive layout | frontend | 58.5 |
| Harden insecure Docker setup with 12 vulnerabilities | code-review | 71.5 |
| Add caching layer to eliminate slow SSR page loads | full-stack | 68.3 |
| Implement zero-trust API authentication layer | backend | 52.5 |
| Implement multi-tenant row-level security in Postgres | backend | 61.1 |
| Write Kubernetes manifests for Node.js microservice | full-stack | 42.3 |
| Implement background job scheduler with persistence | backend | 60.0 |
| Implement transformer inference engine with KV cache | from-scratch | 53.8 |
| Build MCP server for database management | backend | 67.5 |
| Build SaaS admin dashboard from scratch | from-scratch | 50.9 |
| Build production website with auth and members area | frontend | 54.0 |
| Build CLI tool with subcommands and config | from-scratch | 38.3 |
| Build real-time portfolio risk calculator | backend | 36.5 |
| Build LLM evaluation harness with structured grading | backend | 45.0 |
| Fix hallucination and context window bugs in RAG agent | backend | 65.5 |
| Fix race conditions in order matching engine | backend | 80.9 |
| Write complex SQL report with window functions | backend | 73.3 |
| Fix data integrity bugs in denormalized e-commerce schema | debugging | 72.7 |
| Debug and fix 6 broken database triggers and constraints | debugging | 81.8 |
| Fix deadlocking transaction patterns in Flask app | backend | 64.5 |
| Find and fix 4 hidden backdoors in Flask app | debugging | 73.7 |
| Write tests for untested legacy Flask service | code-review | 48.1 |
| Add slash commands and moderation to Discord bot | backend | 60.9 |
| Add retry logic and dead letter queue to Python task queue | backend | 76.2 |
| Fix 12 WCAG accessibility violations in checkout form | frontend | 77.0 |
| Optimize slow Postgres queries in Flask app | backend | 80.6 |
| Fix Node.js stream backpressure causing OOM on large files | backend | 82.4 |
| Add virtual scrolling to table rendering 5000 rows | frontend | 70.1 |
| Build distributed node cluster with gossip protocol | from-scratch | 61.9 |
| Write integration tests for payment flow | code-review | 41.5 |
| Add cursor-based pagination to REST API | backend | 34.2 |
| Add rate limiting middleware | backend | 80.6 |
| Fix auth bypass vulnerability | debugging | 88.0 |
| Implement Stripe webhook handler | backend | 54.3 |
| Zero-downtime schema migration | full-stack | 62.4 |
| Fix flaky test suite | debugging | 74.3 |
| Fix N+1 query in dashboard | backend | 83.8 |
| Refactor monolithic handler to CQRS | refactoring | 72.3 |
| Fix React hydration mismatch | frontend | 73.3 |
| Build terminal UI dashboard | from-scratch | 48.0 |
| Fix memory leak in event handler | debugging | 56.6 |
| Debug race condition in worker pool | debugging | 90.3 |
| Build REST API from scratch | from-scratch | 78.8 |