Back to models
Kimi K2.5
OpenRouter
262K context$0.45/M input$2.25/M output
1493peak 1509
Avg Score
72.7
Avg Cost
$0.04
Score/$
1791.8
Runs
65
Win/Loss/Draw
Scoring Dimensions
Score Distribution
Category ELOs
multi-languagehard
2030from-scratchexpert
2024backendeasy
1985from-scratchmedium
1928frontendhard
1811debugginghard
1635full-stackhard
1632full-stack
1614full-stackmedium
1596debuggingmedium
1595code-reviewhard
1567multi-language
1553debugging
1542backendmedium
1526backendexpert
1513backend
1508from-scratch
1491frontend
1483frontendmedium
1473backendhard
1461debuggingexpert
1451frontendexpert
1440code-review
1435code-reviewmedium
1417from-scratchhard
1376from-scratcheasy
1307frontendeasy
1288refactoring
1204refactoringmedium
1195multi-languageexpert
1135refactoringexpert
475All Results
| Task | Category | Score |
|---|---|---|
| Add Google OAuth2 login to Express app | full-stack | 82.5 |
| Build LLM evaluation harness with structured grading | backend | 73.8 |
| Find and patch all OWASP Top 10 vulnerabilities | debugging | 69.3 |
| Write integration tests for payment flow | code-review | 75.0 |
| Fix hallucination and context window bugs in RAG agent | backend | 49.1 |
| Build distributed node cluster with gossip protocol | from-scratch | 66.0 |
| Add i18n with locale routing to Next.js app | full-stack | 74.7 |
| Implement multi-tenant row-level security in Postgres | backend | 73.7 |
| Port Python CLI to Rust | multi-language | 47.9 |
| Debug race condition in worker pool | debugging | 89.5 |
| Build real-time portfolio risk calculator | backend | 74.9 |
| Build SaaS admin dashboard from scratch | from-scratch | 55.6 |
| Fix race conditions in order matching engine | backend | 74.5 |
| Add cursor-based pagination to REST API | backend | 80.8 |
| Fix broken responsive layout | frontend | 70.1 |
| Find and fix 4 hidden backdoors in Flask app | debugging | 93.8 |
| Convert React app to PWA with offline support | frontend | 66.3 |
| Implement transformer inference engine with KV cache | from-scratch | 86.0 |
| Fix N+1 query in dashboard | backend | 53.4 |
| Fix deadlocking transaction patterns in Flask app | backend | 77.4 |
| Add rate limiting middleware | backend | 81.7 |
| Fix memory leak in event handler | debugging | 81.8 |
| Add retry logic and dead letter queue to Python task queue | backend | 82.9 |
| Fix Node.js stream backpressure causing OOM on large files | backend | 90.3 |
| Write Kubernetes manifests for Node.js microservice | full-stack | 90.2 |
| Add GraphQL layer over REST API | multi-language | 84.1 |
| Code review: identify security vulns | code-review | 79.0 |
| Zero-downtime schema migration | full-stack | 76.1 |
| Debug and fix 6 broken database triggers and constraints | debugging | 71.9 |
| Build terminal UI dashboard | from-scratch | 71.2 |
| Fix 12 WCAG accessibility violations in checkout form | frontend | 84.3 |
| Build MCP server for database management | backend | 84.0 |
| Fix broken GitHub Actions CI pipeline | debugging | 83.3 |
| Fix auth bypass vulnerability | debugging | 88.5 |
| Split 1100-line god file into proper modules | refactoring | 63.8 |
| Implement JWT auth middleware | backend | 53.8 |
| Optimize slow Postgres queries in Flask app | backend | 78.4 |
| Add slash commands and moderation to Discord bot | backend | 72.7 |
| Add file upload with S3 presigned URLs | backend | 79.8 |
| Fix React hydration mismatch | frontend | 83.3 |
| Add WebSocket real-time updates | full-stack | 84.4 |
| Build production website with auth and members area | frontend | 67.1 |
| Build codebase indexer for LLM context windows | from-scratch | 27.5 |
| Add virtual scrolling to table rendering 5000 rows | frontend | 54.0 |
| Replace console.log with structured logging | refactoring | 44.7 |
| Fix data integrity bugs in denormalized e-commerce schema | debugging | 85.0 |
| Implement Stripe webhook handler | backend | 84.4 |
| Harden insecure Docker setup with 12 vulnerabilities | code-review | 76.3 |
| Dockerize Node.js monorepo | full-stack | 75.3 |
| Implement zero-trust API authentication layer | backend | 67.5 |
| Add streaming SSE endpoint for LLM chat | backend | 81.8 |
| Optimize bloated React bundle under 500KB | frontend | 80.5 |
| Build materialized view refresh pipeline for analytics | backend | 76.7 |
| Fix flaky test suite | debugging | 87.5 |
| Add caching layer to eliminate slow SSR page loads | full-stack | 81.2 |
| Write tests for untested legacy Flask service | code-review | 53.3 |
| Build RAG pipeline with vector search | backend | 49.5 |
| Remove AI slop and over-engineering from codebase | refactoring | 74.8 |
| Implement background job scheduler with persistence | backend | 58.0 |
| Migrate callback-hell Express app to async/await | refactoring | 58.0 |
| Write complex SQL report with window functions | backend | 66.8 |
| Build CLI tool with subcommands and config | from-scratch | 74.5 |
| Refactor monolithic handler to CQRS | refactoring | 42.6 |
| Add Redis caching layer to Express API | backend | 85.2 |
| Build REST API from scratch | from-scratch | 77.2 |