Back to models
GLM 4.5
Z.ai
131K context$0.60/M input$2.20/M output
1352peak 1368
Avg Score
65.3
Avg Cost
$0.09
Score/$
728.5
Runs
65
Win/Loss/Draw
Scoring Dimensions
Score Distribution
Category ELOs
from-scratchexpert
1931frontendeasy
1668code-reviewhard
1655debuggingmedium
1523backendmedium
1486debugginghard
1477debugging
1410backend
1384frontendmedium
1381full-stackmedium
1380frontend
1374backendhard
1349code-review
1328full-stack
1322backendexpert
1300refactoringexpert
1295from-scratch
1266debuggingexpert
1266from-scratcheasy
1260full-stackhard
1252refactoring
1241code-reviewmedium
1239refactoringmedium
1174from-scratchhard
1114frontendexpert
1100frontendhard
1043multi-language
1002multi-languageexpert
585backendeasy
365from-scratchmedium
176multi-languagehard
0All Results
| Task | Category | Score |
|---|---|---|
| Implement background job scheduler with persistence | backend | 29.8 |
| Add caching layer to eliminate slow SSR page loads | full-stack | 76.8 |
| Write Kubernetes manifests for Node.js microservice | full-stack | 83.5 |
| Add virtual scrolling to table rendering 5000 rows | frontend | 72.9 |
| Build SaaS admin dashboard from scratch | from-scratch | 40.7 |
| Add cursor-based pagination to REST API | backend | 82.4 |
| Migrate callback-hell Express app to async/await | refactoring | 55.7 |
| Build codebase indexer for LLM context windows | from-scratch | 32.5 |
| Dockerize Node.js monorepo | full-stack | 68.8 |
| Fix memory leak in event handler | debugging | 70.9 |
| Build real-time portfolio risk calculator | backend | 54.9 |
| Implement transformer inference engine with KV cache | from-scratch | 84.0 |
| Write complex SQL report with window functions | backend | 77.4 |
| Write tests for untested legacy Flask service | code-review | 43.0 |
| Implement JWT auth middleware | backend | 80.1 |
| Fix race conditions in order matching engine | backend | 76.3 |
| Fix hallucination and context window bugs in RAG agent | backend | 34.7 |
| Convert React app to PWA with offline support | frontend | 67.7 |
| Build materialized view refresh pipeline for analytics | backend | 73.2 |
| Build LLM evaluation harness with structured grading | backend | 55.3 |
| Port Python CLI to Rust | multi-language | 38.0 |
| Zero-downtime schema migration | full-stack | 53.9 |
| Build production website with auth and members area | frontend | 60.1 |
| Fix 12 WCAG accessibility violations in checkout form | frontend | 72.0 |
| Implement Stripe webhook handler | backend | 72.7 |
| Build distributed node cluster with gossip protocol | from-scratch | 46.8 |
| Code review: identify security vulns | code-review | 70.3 |
| Build REST API from scratch | from-scratch | 75.7 |
| Fix deadlocking transaction patterns in Flask app | backend | 71.0 |
| Fix Node.js stream backpressure causing OOM on large files | backend | 84.5 |
| Find and patch all OWASP Top 10 vulnerabilities | debugging | 67.3 |
| Debug race condition in worker pool | debugging | 85.6 |
| Debug and fix 6 broken database triggers and constraints | debugging | 48.0 |
| Add Redis caching layer to Express API | backend | 77.4 |
| Add WebSocket real-time updates | full-stack | 73.1 |
| Write integration tests for payment flow | code-review | 76.5 |
| Fix N+1 query in dashboard | backend | 47.9 |
| Implement zero-trust API authentication layer | backend | 57.4 |
| Add i18n with locale routing to Next.js app | full-stack | 72.6 |
| Add streaming SSE endpoint for LLM chat | backend | 79.2 |
| Fix auth bypass vulnerability | debugging | 91.5 |
| Add rate limiting middleware | backend | 39.6 |
| Remove AI slop and over-engineering from codebase | refactoring | 77.9 |
| Find and fix 4 hidden backdoors in Flask app | debugging | 80.4 |
| Fix flaky test suite | debugging | 68.8 |
| Implement multi-tenant row-level security in Postgres | backend | 59.0 |
| Fix broken responsive layout | frontend | 76.8 |
| Fix broken GitHub Actions CI pipeline | debugging | 90.9 |
| Split 1100-line god file into proper modules | refactoring | 58.1 |
| Add Google OAuth2 login to Express app | full-stack | 30.4 |
| Add GraphQL layer over REST API | multi-language | 36.8 |
| Build RAG pipeline with vector search | backend | 77.7 |
| Add file upload with S3 presigned URLs | backend | 65.3 |
| Harden insecure Docker setup with 12 vulnerabilities | code-review | 74.7 |
| Optimize bloated React bundle under 500KB | frontend | 64.8 |
| Replace console.log with structured logging | refactoring | 47.8 |
| Build CLI tool with subcommands and config | from-scratch | 55.0 |
| Build MCP server for database management | backend | 78.2 |
| Fix data integrity bugs in denormalized e-commerce schema | debugging | 78.3 |
| Optimize slow Postgres queries in Flask app | backend | 66.0 |
| Add slash commands and moderation to Discord bot | backend | 75.5 |
| Add retry logic and dead letter queue to Python task queue | backend | 79.7 |
| Refactor monolithic handler to CQRS | refactoring | 63.5 |
| Build terminal UI dashboard | from-scratch | 40.8 |
| Fix React hydration mismatch | frontend | 78.0 |