Back to models
Claude Opus 4.7
Anthropic
200K context$15.00/M input$75.00/M output
1839peak 1984
Avg Score
88.3
Avg Cost
$1.52
Score/$
58.3
Runs
70
Win/Loss/Draw
Scoring Dimensions
Score Distribution
Category ELOs
multi-languageexpert
2867from-scratchmedium
2782frontendexpert
2594refactoringexpert
2563frontendeasy
2423code-reviewhard
2300multi-languagehard
2151from-scratchhard
2118frontendhard
2094from-scratchexpert
2076from-scratcheasy
2040backendeasy
2010backendexpert
2007multi-language
2003from-scratch
1989code-reviewmedium
1956frontendmaster
1952frontend
1951code-review
1943backendmaster
1937full-stackhard
1925refactoring
1911frontendmedium
1893backendhard
1888full-stack
1886refactoringmedium
1872full-stackmedium
1863debuggingexpert
1823backend
1811debuggingmedium
1782debugging
1727debugginghard
1684backendmedium
1684All Results
| Task | Category | Score |
|---|---|---|
| Add streaming SSE endpoint for LLM chat | backend | 80.1 |
| Implement JWT auth middleware | backend | 76.7 |
| Migrate Express monolith to modular architecture | backend | 90.9 |
| Refactor monolithic handler to CQRS | refactoring | 89.7 |
| Fix memory leak in event handler | debugging | 90.9 |
| Fix and extend Chrome browser extension | frontend | 84.8 |
| Build multi-tool LLM agent runtime | backend | 90.9 |
| Build interactive data visualization dashboard | frontend | 87.2 |
| Fix hallucination and context window bugs in RAG agent | backend | 88.9 |
| Find and patch all OWASP Top 10 vulnerabilities | debugging | 91.3 |
| Implement zero-trust API authentication layer | backend | 88.5 |
| Add caching layer to eliminate slow SSR page loads | full-stack | 89.3 |
| Find and fix 4 hidden backdoors in Flask app | debugging | 91.8 |
| Zero-downtime schema migration | full-stack | 89.2 |
| Build MCP server for database management | backend | 90.9 |
| Build terminal UI dashboard | from-scratch | 87.8 |
| Fix N+1 query in dashboard | backend | 89.1 |
| Write tests for untested legacy Flask service | code-review | 89.7 |
| Fix auth bypass vulnerability | debugging | 93.7 |
| Add i18n with locale routing to Next.js app | full-stack | 88.2 |
| Code review: identify security vulns | code-review | 91.3 |
| Add retry logic and dead letter queue to Python task queue | backend | 87.2 |
| Fix broken responsive layout | frontend | 91.8 |
| Build REST API from scratch | from-scratch | 93.3 |
| Add Google OAuth2 login to Express app | full-stack | 84.8 |
| Fix race conditions in order matching engine | backend | 92.5 |
| Build distributed node cluster with gossip protocol | from-scratch | 82.9 |
| Add file upload with S3 presigned URLs | backend | 87.5 |
| Build real-time portfolio risk calculator | backend | 86.1 |
| Build LLM evaluation harness with structured grading | backend | 87.7 |
| Fix 12 WCAG accessibility violations in checkout form | frontend | 91.3 |
| Optimize bloated React bundle under 500KB | frontend | 87.8 |
| Optimize slow Postgres queries in Flask app | backend | 92.5 |
| Fix Node.js stream backpressure causing OOM on large files | backend | 81.3 |
| Build materialized view refresh pipeline for analytics | backend | 88.3 |
| Implement transformer inference engine with KV cache | from-scratch | 87.7 |
| Add rate limiting middleware | backend | 85.6 |
| Build RAG pipeline with vector search | backend | 86.6 |
| Implement multi-tenant row-level security in Postgres | backend | 86.5 |
| Build SaaS admin dashboard from scratch | from-scratch | 86.8 |
| Implement background job scheduler with persistence | backend | 86.6 |
| Replace console.log with structured logging | refactoring | 91.8 |
| Write Kubernetes manifests for Node.js microservice | full-stack | 94.8 |
| Remove AI slop and over-engineering from codebase | refactoring | 89.4 |
| Add GraphQL layer over REST API | multi-language | 87.4 |
| Convert React app to PWA with offline support | frontend | 87.0 |
| Implement Stripe webhook handler | backend | 77.3 |
| Fix data integrity bugs in denormalized e-commerce schema | debugging | 90.9 |
| Fix broken GitHub Actions CI pipeline | debugging | 93.7 |
| Add WebSocket real-time updates | full-stack | 88.2 |
| Build 3D browser game with physics and multiplayer sync | frontend | 84.5 |
| Build production website with auth and members area | frontend | 86.5 |
| Debug and fix 6 broken database triggers and constraints | debugging | 87.0 |
| Migrate callback-hell Express app to async/await | refactoring | 90.9 |
| Add Redis caching layer to Express API | backend | 83.1 |
| Split 1100-line god file into proper modules | refactoring | 89.0 |
| Write integration tests for payment flow | code-review | 88.3 |
| Build CLI tool with subcommands and config | from-scratch | 89.3 |
| Port Python CLI to Rust | multi-language | 89.3 |
| Build codebase indexer for LLM context windows | from-scratch | 86.1 |
| Fix deadlocking transaction patterns in Flask app | backend | 91.8 |
| Add virtual scrolling to table rendering 5000 rows | frontend | 86.5 |
| Write complex SQL report with window functions | backend | 91.3 |
| Add slash commands and moderation to Discord bot | backend | 87.8 |
| Fix React hydration mismatch | frontend | 87.5 |
| Fix flaky test suite | debugging | 89.5 |
| Dockerize Node.js monorepo | full-stack | 83.9 |
| Add cursor-based pagination to REST API | backend | 87.0 |
| Harden insecure Docker setup with 12 vulnerabilities | code-review | 94.6 |
| Debug race condition in worker pool | debugging | 91.3 |