Back to models
GPT 5.1 Codex Mini
OpenAI
400K context$3.00/M input$15.00/M output
1747peak 1765
Avg Score
81.0
Avg Cost
$1.84
Score/$
44.0
Runs
54
Win/Loss/Draw
Scoring Dimensions
Score Distribution
Category ELOs
multi-languageexpert
3238code-reviewhard
3008from-scratchmedium
2714frontendexpert
2354from-scratchhard
2327code-reviewmedium
2289code-review
2238frontendhard
2185multi-languagehard
2110multi-language
2098from-scratchexpert
2072from-scratch
2010backendeasy
2007refactoringexpert
1984debuggingmedium
1919from-scratcheasy
1918backendmedium
1776backendexpert
1762backend
1734backendhard
1720full-stack
1717full-stackhard
1715frontend
1711refactoring
1705debugging
1624debuggingexpert
1621frontendmedium
1588debugginghard
1528All Results
| Task | Category | Score |
|---|---|---|
| Harden insecure Docker setup with 12 vulnerabilities | code-review | — |
| Build codebase indexer for LLM context windows | from-scratch | — |
| Code review: identify security vulns | code-review | — |
| Dockerize Node.js monorepo | full-stack | — |
| Split 1100-line god file into proper modules | refactoring | — |
| Build RAG pipeline with vector search | backend | — |
| Add i18n with locale routing to Next.js app | full-stack | — |
| Remove AI slop and over-engineering from codebase | refactoring | — |
| Write Kubernetes manifests for Node.js microservice | full-stack | — |
| Optimize bloated React bundle under 500KB | frontend | 79.4 |
| Implement multi-tenant row-level security in Postgres | backend | 82.5 |
| Implement zero-trust API authentication layer | backend | 77.7 |
| Fix broken GitHub Actions CI pipeline | debugging | 88.3 |
| Find and patch all OWASP Top 10 vulnerabilities | debugging | 77.8 |
| Build distributed node cluster with gossip protocol | from-scratch | 72.5 |
| Convert React app to PWA with offline support | frontend | 79.7 |
| Find and fix 4 hidden backdoors in Flask app | debugging | 87.0 |
| Build production website with auth and members area | frontend | 75.5 |
| Build SaaS admin dashboard from scratch | from-scratch | 86.4 |
| Build MCP server for database management | backend | 69.2 |
| Implement transformer inference engine with KV cache | from-scratch | 86.6 |
| Implement background job scheduler with persistence | backend | 82.0 |
| Build CLI tool with subcommands and config | from-scratch | 82.9 |
| Build LLM evaluation harness with structured grading | backend | 61.5 |
| Build real-time portfolio risk calculator | backend | 72.2 |
| Add Redis caching layer to Express API | backend | 80.0 |
| Fix race conditions in order matching engine | backend | 90.9 |
| Debug and fix 6 broken database triggers and constraints | debugging | 79.8 |
| Fix data integrity bugs in denormalized e-commerce schema | debugging | 80.8 |
| Write complex SQL report with window functions | backend | 79.5 |
| Build materialized view refresh pipeline for analytics | backend | 75.3 |
| Fix deadlocking transaction patterns in Flask app | backend | 79.8 |
| Fix hallucination and context window bugs in RAG agent | backend | 77.3 |
| Write tests for untested legacy Flask service | code-review | 92.5 |
| Add Google OAuth2 login to Express app | full-stack | 82.0 |
| Optimize slow Postgres queries in Flask app | backend | 81.0 |
| Add slash commands and moderation to Discord bot | backend | 83.8 |
| Add virtual scrolling to table rendering 5000 rows | frontend | 81.8 |
| Fix 12 WCAG accessibility violations in checkout form | frontend | 90.4 |
| Add GraphQL layer over REST API | multi-language | 80.5 |
| Write integration tests for payment flow | code-review | 81.0 |
| Zero-downtime schema migration | full-stack | 76.5 |
| Add rate limiting middleware | backend | 83.5 |
| Implement Stripe webhook handler | backend | 80.5 |
| Port Python CLI to Rust | multi-language | 90.3 |
| Fix flaky test suite | debugging | 88.4 |
| Add cursor-based pagination to REST API | backend | 87.9 |
| Fix N+1 query in dashboard | backend | 82.9 |
| Fix memory leak in event handler | debugging | 85.8 |
| Refactor monolithic handler to CQRS | refactoring | 72.7 |
| Debug race condition in worker pool | debugging | 76.6 |
| Fix React hydration mismatch | frontend | 69.2 |
| Build terminal UI dashboard | from-scratch | 82.2 |
| Build REST API from scratch | from-scratch | 89.3 |