Back to models
Gemini 2.5 Pro
OpenRouter
1049K context$1.25/M input$10.00/M output
1436peak 1437
Avg Score
68.4
Avg Cost
$0.27
Score/$
257.6
Runs
116
Win/Loss/Draw
Scoring Dimensions
Score Distribution
Category ELOs
frontendhard
1979from-scratchexpert
1884debuggingmedium
1839frontendeasy
1638full-stackmedium
1582backendeasy
1567debugging
1536backendmedium
1497debuggingexpert
1493from-scratchhard
1493multi-languageexpert
1490frontend
1489debugginghard
1474frontendexpert
1467from-scratch
1464full-stack
1443backend
1443backendexpert
1427frontendmedium
1419backendhard
1378refactoringmedium
1367refactoring
1315full-stackhard
1276multi-language
1253from-scratchmedium
1235code-reviewmedium
1182code-review
1159from-scratcheasy
1105code-reviewhard
193refactoringexpert
0multi-languagehard
0All Results
| Task | Category | Score |
|---|---|---|
| Build SaaS admin dashboard from scratch | from-scratch | 50.1 |
| Split 1100-line god file into proper modules | refactoring | 62.7 |
| Implement JWT auth middleware | backend | 52.0 |
| Convert React app to PWA with offline support | frontend | 52.1 |
| Add file upload with S3 presigned URLs | backend | 74.2 |
| Implement multi-tenant row-level security in Postgres | backend | 66.7 |
| Code review: identify security vulns | code-review | 73.0 |
| Build terminal UI dashboard | from-scratch | 59.3 |
| Build production website with auth and members area | frontend | 65.9 |
| Add retry logic and dead letter queue to Python task queue | backend | 70.5 |
| Add slash commands and moderation to Discord bot | backend | 78.9 |
| Dockerize Node.js monorepo | full-stack | 75.5 |
| Fix 12 WCAG accessibility violations in checkout form | frontend | 86.5 |
| Add virtual scrolling to table rendering 5000 rows | frontend | 85.6 |
| Implement zero-trust API authentication layer | backend | 68.8 |
| Write integration tests for payment flow | code-review | 41.4 |
| Fix React hydration mismatch | frontend | 38.5 |
| Add WebSocket real-time updates | full-stack | 58.7 |
| Harden insecure Docker setup with 12 vulnerabilities | code-review | 65.2 |
| Build distributed node cluster with gossip protocol | from-scratch | 58.0 |
| Implement background job scheduler with persistence | backend | 40.2 |
| Add caching layer to eliminate slow SSR page loads | full-stack | 85.2 |
| Write complex SQL report with window functions | backend | 40.0 |
| Fix hallucination and context window bugs in RAG agent | backend | 63.8 |
| Fix N+1 query in dashboard | backend | 69.7 |
| Zero-downtime schema migration | full-stack | 48.1 |
| Build real-time portfolio risk calculator | backend | 58.6 |
| Refactor monolithic handler to CQRS | refactoring | 28.3 |
| Optimize bloated React bundle under 500KB | frontend | 79.7 |
| Build CLI tool with subcommands and config | from-scratch | 73.3 |
| Implement transformer inference engine with KV cache | from-scratch | 82.6 |
| Fix broken GitHub Actions CI pipeline | debugging | 88.8 |
| Add GraphQL layer over REST API | multi-language | 34.6 |
| Implement Stripe webhook handler | backend | 66.5 |
| Find and patch all OWASP Top 10 vulnerabilities | debugging | 31.8 |
| Replace console.log with structured logging | refactoring | 60.8 |
| Add streaming SSE endpoint for LLM chat | backend | 82.4 |
| Fix race conditions in order matching engine | backend | 79.1 |
| Build materialized view refresh pipeline for analytics | backend | 72.8 |
| Fix Node.js stream backpressure causing OOM on large files | backend | 43.4 |
| Build MCP server for database management | backend | 82.4 |
| Build codebase indexer for LLM context windows | from-scratch | 52.9 |
| Fix flaky test suite | debugging | 93.0 |
| Find and fix 4 hidden backdoors in Flask app | debugging | 90.9 |
| Add i18n with locale routing to Next.js app | full-stack | 75.7 |
| Add rate limiting middleware | backend | 73.5 |
| Debug and fix 6 broken database triggers and constraints | debugging | 88.8 |
| Write tests for untested legacy Flask service | code-review | 33.4 |
| Optimize slow Postgres queries in Flask app | backend | 86.3 |
| Fix auth bypass vulnerability | debugging | 78.5 |
| Debug race condition in worker pool | debugging | 88.0 |
| Fix broken responsive layout | frontend | 75.0 |
| Build RAG pipeline with vector search | backend | 37.8 |
| Fix memory leak in event handler | debugging | 34.3 |
| Migrate callback-hell Express app to async/await | refactoring | 64.4 |
| Build LLM evaluation harness with structured grading | backend | 68.3 |
| Add Redis caching layer to Express API | backend | 50.5 |
| Remove AI slop and over-engineering from codebase | refactoring | 75.3 |
| Port Python CLI to Rust | multi-language | 52.2 |
| Build REST API from scratch | from-scratch | 70.2 |
| Convert React app to PWA with offline support | frontend | 66.8 |
| Dockerize Node.js monorepo | full-stack | 69.0 |
| Implement multi-tenant row-level security in Postgres | backend | 56.5 |
| Remove AI slop and over-engineering from codebase | refactoring | 84.5 |
| Write Kubernetes manifests for Node.js microservice | full-stack | 82.3 |
| Implement JWT auth middleware | backend | 75.0 |
| Harden insecure Docker setup with 12 vulnerabilities | code-review | 78.3 |
| Build codebase indexer for LLM context windows | from-scratch | 35.0 |
| Add caching layer to eliminate slow SSR page loads | full-stack | 88.1 |
| Add streaming SSE endpoint for LLM chat | backend | 72.7 |
| Fix broken responsive layout | frontend | 68.8 |
| Add i18n with locale routing to Next.js app | full-stack | 63.7 |
| Split 1100-line god file into proper modules | refactoring | 75.0 |
| Optimize bloated React bundle under 500KB | frontend | 70.1 |
| Replace console.log with structured logging | refactoring | 40.9 |
| Implement zero-trust API authentication layer | backend | 70.5 |
| Find and patch all OWASP Top 10 vulnerabilities | debugging | 69.4 |
| Add Redis caching layer to Express API | backend | 62.7 |
| Implement background job scheduler with persistence | backend | 73.2 |
| Implement transformer inference engine with KV cache | from-scratch | 84.0 |
| Build MCP server for database management | backend | 51.9 |
| Build SaaS admin dashboard from scratch | from-scratch | 68.0 |
| Build real-time portfolio risk calculator | backend | 53.7 |
| Fix hallucination and context window bugs in RAG agent | backend | 74.1 |
| Build production website with auth and members area | frontend | 54.3 |
| Build LLM evaluation harness with structured grading | backend | 58.0 |
| Build CLI tool with subcommands and config | from-scratch | 70.5 |
| Fix race conditions in order matching engine | backend | 67.2 |
| Build materialized view refresh pipeline for analytics | backend | 69.9 |
| Fix deadlocking transaction patterns in Flask app | backend | 65.5 |
| Debug and fix 6 broken database triggers and constraints | debugging | 81.8 |
| Write complex SQL report with window functions | backend | 72.1 |
| Fix data integrity bugs in denormalized e-commerce schema | debugging | 82.2 |
| Build RAG pipeline with vector search | backend | 72.8 |
| Find and fix 4 hidden backdoors in Flask app | debugging | 82.0 |
| Write tests for untested legacy Flask service | code-review | 60.5 |
| Fix 12 WCAG accessibility violations in checkout form | frontend | 81.8 |
| Optimize slow Postgres queries in Flask app | backend | 85.9 |
| Add retry logic and dead letter queue to Python task queue | backend | 72.8 |
| Add slash commands and moderation to Discord bot | backend | 81.8 |
| Fix Node.js stream backpressure causing OOM on large files | backend | 63.9 |
| Build distributed node cluster with gossip protocol | from-scratch | 79.8 |
| Write integration tests for payment flow | code-review | 68.5 |
| Add GraphQL layer over REST API | multi-language | 73.0 |
| Fix auth bypass vulnerability | debugging | 95.0 |
| Add rate limiting middleware | backend | 78.7 |
| Zero-downtime schema migration | full-stack | 76.5 |
| Add cursor-based pagination to REST API | backend | 90.0 |
| Fix flaky test suite | debugging | 83.1 |
| Fix N+1 query in dashboard | backend | 77.7 |
| Refactor monolithic handler to CQRS | refactoring | 79.9 |
| Fix memory leak in event handler | debugging | 62.0 |
| Fix React hydration mismatch | frontend | 76.4 |
| Build terminal UI dashboard | from-scratch | 73.4 |
| Debug race condition in worker pool | debugging | 88.8 |
| Build REST API from scratch | from-scratch | 86.0 |