Back to models
Gemini 3.1 Pro Preview
OpenRouter
1049K context$2.00/M input$12.00/M output
1672peak 1676
Avg Score
75.7
Avg Cost
$0.57
Score/$
132.6
Runs
101
Win/Loss/Draw
Scoring Dimensions
Score Distribution
Category ELOs
multi-languageexpert
3238frontendeasy
2632backendeasy
2631refactoringexpert
2558from-scratchmedium
2530frontendexpert
2354code-reviewhard
2125from-scratchexpert
2090from-scratchhard
2015from-scratch
1911multi-languagehard
1829from-scratcheasy
1819refactoring
1818frontendhard
1806frontend
1737backendhard
1724refactoringmedium
1724multi-language
1684backend
1675code-review
1670backendmedium
1667debuggingexpert
1660full-stackmedium
1633code-reviewmedium
1629frontendmedium
1627backendexpert
1612full-stack
1605full-stackhard
1604debugginghard
1593debugging
1489debuggingmedium
992All Results
| Task | Category | Score |
|---|---|---|
| Replace console.log with structured logging | refactoring | 68.9 |
| Build SaaS admin dashboard from scratch | from-scratch | 63.6 |
| Fix Node.js stream backpressure causing OOM on large files | backend | 86.3 |
| Find and patch all OWASP Top 10 vulnerabilities | debugging | 69.7 |
| Build LLM evaluation harness with structured grading | backend | 81.7 |
| Find and fix 4 hidden backdoors in Flask app | debugging | 90.7 |
| Fix React hydration mismatch | frontend | 71.1 |
| Implement background job scheduler with persistence | backend | 79.7 |
| Implement multi-tenant row-level security in Postgres | backend | 80.3 |
| Write complex SQL report with window functions | backend | 78.1 |
| Fix broken responsive layout | frontend | 78.0 |
| Write tests for untested legacy Flask service | code-review | 49.9 |
| Build codebase indexer for LLM context windows | from-scratch | 54.8 |
| Implement Stripe webhook handler | backend | 81.2 |
| Build CLI tool with subcommands and config | from-scratch | 82.5 |
| Fix race conditions in order matching engine | backend | 91.8 |
| Add streaming SSE endpoint for LLM chat | backend | 87.7 |
| Split 1100-line god file into proper modules | refactoring | 61.3 |
| Debug and fix 6 broken database triggers and constraints | debugging | 90.0 |
| Build terminal UI dashboard | from-scratch | 65.3 |
| Migrate callback-hell Express app to async/await | refactoring | 65.0 |
| Fix 12 WCAG accessibility violations in checkout form | frontend | 85.5 |
| Code review: identify security vulns | code-review | 78.1 |
| Fix memory leak in event handler | debugging | 48.9 |
| Fix auth bypass vulnerability | debugging | 92.1 |
| Zero-downtime schema migration | full-stack | 82.8 |
| Add WebSocket real-time updates | full-stack | 76.5 |
| Build real-time portfolio risk calculator | backend | 65.0 |
| Add retry logic and dead letter queue to Python task queue | backend | 88.3 |
| Optimize slow Postgres queries in Flask app | backend | 85.0 |
| Add cursor-based pagination to REST API | backend | 79.2 |
| Build distributed node cluster with gossip protocol | from-scratch | 61.9 |
| Build production website with auth and members area | frontend | 64.6 |
| Fix data integrity bugs in denormalized e-commerce schema | debugging | 84.2 |
| Add rate limiting middleware | backend | 87.5 |
| Remove AI slop and over-engineering from codebase | refactoring | 85.8 |
| Add caching layer to eliminate slow SSR page loads | full-stack | 89.2 |
| Add Redis caching layer to Express API | backend | 46.5 |
| Fix broken GitHub Actions CI pipeline | debugging | 67.5 |
| Add GraphQL layer over REST API | multi-language | 78.5 |
| Port Python CLI to Rust | multi-language | 76.5 |
| Code review: identify security vulns | code-review | 83.2 |
| Add WebSocket real-time updates | full-stack | 84.2 |
| Build RAG pipeline with vector search | backend | 78.3 |
| Add file upload with S3 presigned URLs | backend | 44.3 |
| Build codebase indexer for LLM context windows | from-scratch | 57.6 |
| Implement zero-trust API authentication layer | backend | 67.7 |
| Add i18n with locale routing to Next.js app | full-stack | 35.8 |
| Fix broken responsive layout | frontend | 89.5 |
| Split 1100-line god file into proper modules | refactoring | 86.8 |
| Implement JWT auth middleware | backend | 69.0 |
| Write Kubernetes manifests for Node.js microservice | full-stack | 93.8 |
| Convert React app to PWA with offline support | frontend | 63.4 |
| Optimize bloated React bundle under 500KB | frontend | 76.6 |
| Remove AI slop and over-engineering from codebase | refactoring | 73.5 |
| Add caching layer to eliminate slow SSR page loads | full-stack | 87.6 |
| Dockerize Node.js monorepo | full-stack | 63.5 |
| Find and patch all OWASP Top 10 vulnerabilities | debugging | 74.6 |
| Replace console.log with structured logging | refactoring | 64.2 |
| Add streaming SSE endpoint for LLM chat | backend | 69.8 |
| Harden insecure Docker setup with 12 vulnerabilities | code-review | 87.2 |
| Implement multi-tenant row-level security in Postgres | backend | 42.4 |
| Write tests for untested legacy Flask service | code-review | 42.9 |
| Fix deadlocking transaction patterns in Flask app | backend | 57.1 |
| Build production website with auth and members area | frontend | 74.9 |
| Build CLI tool with subcommands and config | from-scratch | 76.6 |
| Build SaaS admin dashboard from scratch | from-scratch | 76.9 |
| Implement transformer inference engine with KV cache | from-scratch | 89.8 |
| Implement background job scheduler with persistence | backend | 80.7 |
| Build MCP server for database management | backend | 86.1 |
| Build real-time portfolio risk calculator | backend | 72.8 |
| Fix hallucination and context window bugs in RAG agent | backend | 64.5 |
| Build LLM evaluation harness with structured grading | backend | 80.3 |
| Debug and fix 6 broken database triggers and constraints | debugging | 72.3 |
| Fix data integrity bugs in denormalized e-commerce schema | debugging | 78.3 |
| Fix race conditions in order matching engine | backend | 90.5 |
| Write complex SQL report with window functions | backend | 65.6 |
| Build materialized view refresh pipeline for analytics | backend | 66.3 |
| Find and fix 4 hidden backdoors in Flask app | debugging | 87.4 |
| Optimize slow Postgres queries in Flask app | backend | 90.4 |
| Add virtual scrolling to table rendering 5000 rows | frontend | 80.5 |
| Add Google OAuth2 login to Express app | full-stack | 76.0 |
| Fix Node.js stream backpressure causing OOM on large files | backend | 81.9 |
| Add slash commands and moderation to Discord bot | backend | 85.1 |
| Add retry logic and dead letter queue to Python task queue | backend | 89.4 |
| Fix 12 WCAG accessibility violations in checkout form | frontend | 83.0 |
| Write integration tests for payment flow | code-review | 74.7 |
| Build distributed node cluster with gossip protocol | from-scratch | 85.8 |
| Fix auth bypass vulnerability | debugging | 92.9 |
| Refactor monolithic handler to CQRS | refactoring | 80.5 |
| Add rate limiting middleware | backend | 85.2 |
| Zero-downtime schema migration | full-stack | 64.3 |
| Fix React hydration mismatch | frontend | 79.5 |
| Implement Stripe webhook handler | backend | 76.7 |
| Fix flaky test suite | debugging | 63.8 |
| Build terminal UI dashboard | from-scratch | 79.6 |
| Fix N+1 query in dashboard | backend | 90.6 |
| Add cursor-based pagination to REST API | backend | 85.2 |
| Debug race condition in worker pool | debugging | 87.0 |
| Fix memory leak in event handler | debugging | 73.0 |
| Build REST API from scratch | from-scratch | 86.3 |