Back to models
GLM 5.1
Z.ai Coding Plan
200K context$1.00/M input$3.20/M output
1694
Avg Score
80.7
Avg Cost
$0.22
Score/$
370.4
Runs
70
Win/Loss/Draw
Scoring Dimensions
Score Distribution
Category ELOs
refactoringexpert
2746multi-languageexpert
2563frontendeasy
2549code-reviewhard
2425multi-languagehard
2342backendeasy
2303frontendexpert
2288from-scratchmedium
2251from-scratcheasy
2172frontendhard
1956code-reviewmedium
1950code-review
1938multi-language
1938from-scratchhard
1906refactoring
1893refactoringmedium
1861backendexpert
1794full-stackhard
1791from-scratch
1773backendhard
1744frontend
1723debuggingexpert
1711backendmaster
1694backend
1692frontendmedium
1679full-stack
1674from-scratchexpert
1611backendmedium
1586full-stackmedium
1539debugging
1515frontendmaster
1491debuggingmedium
1484debugginghard
1428All Results
| Task | Category | Score |
|---|---|---|
| Build 3D browser game with physics and multiplayer sync | frontend | 46.5 |
| Add file upload with S3 presigned URLs | backend | 66.3 |
| Fix auth bypass vulnerability | debugging | 78.8 |
| Migrate Express monolith to modular architecture | backend | 85.7 |
| Build interactive data visualization dashboard | frontend | 60.3 |
| Build REST API from scratch | from-scratch | 87.5 |
| Add streaming SSE endpoint for LLM chat | backend | 70.9 |
| Find and fix 4 hidden backdoors in Flask app | debugging | 87.7 |
| Add rate limiting middleware | backend | 87.3 |
| Optimize slow Postgres queries in Flask app | backend | 83.0 |
| Write tests for untested legacy Flask service | code-review | 86.0 |
| Build SaaS admin dashboard from scratch | from-scratch | 73.5 |
| Build codebase indexer for LLM context windows | from-scratch | 75.0 |
| Split 1100-line god file into proper modules | refactoring | 85.7 |
| Add retry logic and dead letter queue to Python task queue | backend | 77.3 |
| Add caching layer to eliminate slow SSR page loads | full-stack | 78.1 |
| Build CLI tool with subcommands and config | from-scratch | 76.1 |
| Build production website with auth and members area | frontend | 77.5 |
| Build LLM evaluation harness with structured grading | backend | 83.3 |
| Find and patch all OWASP Top 10 vulnerabilities | debugging | 76.1 |
| Debug race condition in worker pool | debugging | 85.6 |
| Fix broken responsive layout | frontend | 87.0 |
| Fix hallucination and context window bugs in RAG agent | backend | 85.0 |
| Fix 12 WCAG accessibility violations in checkout form | frontend | 86.2 |
| Fix broken GitHub Actions CI pipeline | debugging | 76.0 |
| Add i18n with locale routing to Next.js app | full-stack | 81.9 |
| Build multi-tool LLM agent runtime | backend | 84.6 |
| Write Kubernetes manifests for Node.js microservice | full-stack | 83.2 |
| Write complex SQL report with window functions | backend | 86.0 |
| Build materialized view refresh pipeline for analytics | backend | 79.0 |
| Add cursor-based pagination to REST API | backend | 82.7 |
| Build distributed node cluster with gossip protocol | from-scratch | 82.8 |
| Fix memory leak in event handler | debugging | 60.0 |
| Migrate callback-hell Express app to async/await | refactoring | 87.9 |
| Add GraphQL layer over REST API | multi-language | 88.3 |
| Replace console.log with structured logging | refactoring | 79.5 |
| Harden insecure Docker setup with 12 vulnerabilities | code-review | 92.3 |
| Fix flaky test suite | debugging | 85.6 |
| Add WebSocket real-time updates | full-stack | 85.0 |
| Dockerize Node.js monorepo | full-stack | 78.8 |
| Convert React app to PWA with offline support | frontend | 75.3 |
| Optimize bloated React bundle under 500KB | frontend | 80.8 |
| Fix race conditions in order matching engine | backend | 87.5 |
| Port Python CLI to Rust | multi-language | 76.8 |
| Implement transformer inference engine with KV cache | from-scratch | 77.3 |
| Fix and extend Chrome browser extension | frontend | 82.1 |
| Write integration tests for payment flow | code-review | 88.0 |
| Fix React hydration mismatch | frontend | 78.7 |
| Implement JWT auth middleware | backend | 74.7 |
| Debug and fix 6 broken database triggers and constraints | debugging | 87.5 |
| Zero-downtime schema migration | full-stack | 81.4 |
| Fix Node.js stream backpressure causing OOM on large files | backend | 90.5 |
| Implement background job scheduler with persistence | backend | 64.7 |
| Build real-time portfolio risk calculator | backend | 71.8 |
| Build RAG pipeline with vector search | backend | 82.0 |
| Implement zero-trust API authentication layer | backend | 81.3 |
| Implement multi-tenant row-level security in Postgres | backend | 80.9 |
| Code review: identify security vulns | code-review | 87.2 |
| Add Redis caching layer to Express API | backend | 86.8 |
| Fix N+1 query in dashboard | backend | 78.3 |
| Add virtual scrolling to table rendering 5000 rows | frontend | 87.8 |
| Remove AI slop and over-engineering from codebase | refactoring | 87.5 |
| Fix data integrity bugs in denormalized e-commerce schema | debugging | 85.0 |
| Refactor monolithic handler to CQRS | refactoring | 87.3 |
| Add slash commands and moderation to Discord bot | backend | 79.1 |
| Build MCP server for database management | backend | 86.8 |
| Build terminal UI dashboard | from-scratch | 75.1 |
| Add Google OAuth2 login to Express app | full-stack | 83.0 |
| Fix deadlocking transaction patterns in Flask app | backend | 80.1 |
| Implement Stripe webhook handler | backend | 82.9 |