Back to models
GPT 5.2 Codex
OpenRouter
400K context$1.75/M input$14.00/M output
1642peak 1659
Avg Score
78.5
Avg Cost
$0.13
Score/$
612.6
Runs
65
Win/Loss/Draw
Scoring Dimensions
Score Distribution
Category ELOs
code-reviewhard
2369from-scratchexpert
2113from-scratchmedium
2020frontendhard
1994multi-languageexpert
1923debuggingexpert
1845backendexpert
1754from-scratcheasy
1739code-review
1737frontendmedium
1728backendmedium
1712debugging
1701full-stackhard
1696code-reviewmedium
1695debugginghard
1694full-stack
1677backend
1674from-scratch
1665frontend
1663full-stackmedium
1662from-scratchhard
1658frontendeasy
1657backendhard
1643debuggingmedium
1642refactoringmedium
1494refactoring
1479backendeasy
1419multi-language
1338frontendexpert
1331refactoringexpert
1163multi-languagehard
125All Results
| Task | Category | Score |
|---|---|---|
| Write complex SQL report with window functions | backend | 75.1 |
| Debug and fix 6 broken database triggers and constraints | debugging | 93.0 |
| Migrate callback-hell Express app to async/await | refactoring | 68.2 |
| Build distributed node cluster with gossip protocol | from-scratch | 54.5 |
| Harden insecure Docker setup with 12 vulnerabilities | code-review | 89.3 |
| Build codebase indexer for LLM context windows | from-scratch | 59.3 |
| Replace console.log with structured logging | refactoring | 64.7 |
| Fix data integrity bugs in denormalized e-commerce schema | debugging | 93.7 |
| Add caching layer to eliminate slow SSR page loads | full-stack | 81.6 |
| Fix auth bypass vulnerability | debugging | 92.2 |
| Fix race conditions in order matching engine | backend | 92.5 |
| Fix hallucination and context window bugs in RAG agent | backend | 61.1 |
| Optimize slow Postgres queries in Flask app | backend | 89.3 |
| Fix broken GitHub Actions CI pipeline | debugging | 79.7 |
| Fix deadlocking transaction patterns in Flask app | backend | 74.5 |
| Add i18n with locale routing to Next.js app | full-stack | 81.8 |
| Fix 12 WCAG accessibility violations in checkout form | frontend | 87.7 |
| Find and patch all OWASP Top 10 vulnerabilities | debugging | 74.7 |
| Build real-time portfolio risk calculator | backend | 67.8 |
| Implement zero-trust API authentication layer | backend | 77.9 |
| Add streaming SSE endpoint for LLM chat | backend | 84.8 |
| Remove AI slop and over-engineering from codebase | refactoring | 89.3 |
| Optimize bloated React bundle under 500KB | frontend | 78.7 |
| Add Redis caching layer to Express API | backend | 84.6 |
| Implement background job scheduler with persistence | backend | 80.0 |
| Build materialized view refresh pipeline for analytics | backend | 78.7 |
| Build CLI tool with subcommands and config | from-scratch | 76.6 |
| Zero-downtime schema migration | full-stack | 74.4 |
| Add file upload with S3 presigned URLs | backend | 87.5 |
| Split 1100-line god file into proper modules | refactoring | 60.3 |
| Build MCP server for database management | backend | 89.5 |
| Write integration tests for payment flow | code-review | 88.3 |
| Add WebSocket real-time updates | full-stack | 83.7 |
| Implement multi-tenant row-level security in Postgres | backend | 88.4 |
| Build SaaS admin dashboard from scratch | from-scratch | 76.0 |
| Build terminal UI dashboard | from-scratch | 72.9 |
| Implement JWT auth middleware | backend | 53.3 |
| Add slash commands and moderation to Discord bot | backend | 84.0 |
| Fix N+1 query in dashboard | backend | 78.2 |
| Implement transformer inference engine with KV cache | from-scratch | 88.2 |
| Fix React hydration mismatch | frontend | 80.5 |
| Fix memory leak in event handler | debugging | 89.3 |
| Build RAG pipeline with vector search | backend | 43.5 |
| Build LLM evaluation harness with structured grading | backend | 81.3 |
| Write Kubernetes manifests for Node.js microservice | full-stack | 93.7 |
| Add retry logic and dead letter queue to Python task queue | backend | 86.9 |
| Add virtual scrolling to table rendering 5000 rows | frontend | 87.8 |
| Implement Stripe webhook handler | backend | 85.8 |
| Add GraphQL layer over REST API | multi-language | 41.0 |
| Add cursor-based pagination to REST API | backend | 75.5 |
| Fix flaky test suite | debugging | 93.3 |
| Find and fix 4 hidden backdoors in Flask app | debugging | 88.3 |
| Dockerize Node.js monorepo | full-stack | 76.5 |
| Build REST API from scratch | from-scratch | 82.5 |
| Code review: identify security vulns | code-review | 82.0 |
| Convert React app to PWA with offline support | frontend | 82.5 |
| Fix Node.js stream backpressure causing OOM on large files | backend | 89.2 |
| Build production website with auth and members area | frontend | 64.8 |
| Add Google OAuth2 login to Express app | full-stack | 84.1 |
| Port Python CLI to Rust | multi-language | 67.4 |
| Add rate limiting middleware | backend | 72.2 |
| Debug race condition in worker pool | debugging | 92.0 |
| Write tests for untested legacy Flask service | code-review | 72.3 |
| Refactor monolithic handler to CQRS | refactoring | 60.5 |
| Fix broken responsive layout | frontend | 76.5 |