Back to models
GLM 5.2
Z.ai Coding Plan
1000K context$1.40/M input$4.40/M output
1795peak 1892
Avg Score
85.3
Avg Cost
$0.39
Score/$
217.1
Runs
70
Win/Loss/Draw
Scoring Dimensions
Score Distribution
Category ELOs
multi-languageexpert
2921from-scratchmedium
2769refactoringexpert
2569frontendexpert
2459from-scratcheasy
2388multi-languagehard
2349code-reviewhard
2307backendeasy
2170from-scratchhard
2123multi-language
2095from-scratch
1979code-reviewmedium
1973backendexpert
1969code-review
1943frontendhard
1942from-scratchexpert
1922refactoring
1906refactoringmedium
1889full-stackhard
1886debuggingexpert
1867full-stack
1860full-stackmedium
1854backendhard
1817debuggingmedium
1776backend
1771frontendeasy
1771frontend
1732debugging
1719frontendmedium
1712backendmedium
1665debugginghard
1656frontendmaster
1604backendmaster
1572All Results
| Task | Category | Score |
|---|---|---|
| Fix hallucination and context window bugs in RAG agent | backend | 87.9 |
| Implement background job scheduler with persistence | backend | 81.5 |
| Find and patch all OWASP Top 10 vulnerabilities | debugging | 88.1 |
| Fix N+1 query in dashboard | backend | 77.7 |
| Build CLI tool with subcommands and config | from-scratch | 88.4 |
| Build materialized view refresh pipeline for analytics | backend | 85.5 |
| Write Kubernetes manifests for Node.js microservice | full-stack | 90.3 |
| Fix data integrity bugs in denormalized e-commerce schema | debugging | 90.5 |
| Build 3D browser game with physics and multiplayer sync | frontend | 71.0 |
| Fix memory leak in event handler | debugging | 78.1 |
| Build interactive data visualization dashboard | frontend | 79.5 |
| Implement multi-tenant row-level security in Postgres | backend | 87.0 |
| Build MCP server for database management | backend | 83.5 |
| Add virtual scrolling to table rendering 5000 rows | frontend | 85.6 |
| Write complex SQL report with window functions | backend | 78.5 |
| Optimize bloated React bundle under 500KB | frontend | 73.0 |
| Fix broken responsive layout | frontend | 79.6 |
| Implement Stripe webhook handler | backend | 87.9 |
| Fix Node.js stream backpressure causing OOM on large files | backend | 91.9 |
| Build SaaS admin dashboard from scratch | from-scratch | 87.9 |
| Port Python CLI to Rust | multi-language | 89.0 |
| Fix auth bypass vulnerability | debugging | 90.4 |
| Add i18n with locale routing to Next.js app | full-stack | 81.0 |
| Zero-downtime schema migration | full-stack | 88.5 |
| Build real-time portfolio risk calculator | backend | 86.5 |
| Optimize slow Postgres queries in Flask app | backend | 84.3 |
| Build multi-tool LLM agent runtime | backend | 73.8 |
| Remove AI slop and over-engineering from codebase | refactoring | 88.3 |
| Add caching layer to eliminate slow SSR page loads | full-stack | 87.0 |
| Add slash commands and moderation to Discord bot | backend | 87.3 |
| Implement transformer inference engine with KV cache | from-scratch | 83.4 |
| Build codebase indexer for LLM context windows | from-scratch | 75.3 |
| Fix flaky test suite | debugging | 88.7 |
| Implement zero-trust API authentication layer | backend | 86.5 |
| Fix and extend Chrome browser extension | frontend | 75.0 |
| Build RAG pipeline with vector search | backend | 87.0 |
| Debug race condition in worker pool | debugging | 93.0 |
| Fix deadlocking transaction patterns in Flask app | backend | 90.4 |
| Fix 12 WCAG accessibility violations in checkout form | frontend | 86.5 |
| Convert React app to PWA with offline support | frontend | 85.7 |
| Split 1100-line god file into proper modules | refactoring | 86.8 |
| Add cursor-based pagination to REST API | backend | 86.9 |
| Add Google OAuth2 login to Express app | full-stack | 85.7 |
| Migrate callback-hell Express app to async/await | refactoring | 83.9 |
| Build production website with auth and members area | frontend | 83.5 |
| Build distributed node cluster with gossip protocol | from-scratch | 87.3 |
| Fix race conditions in order matching engine | backend | 92.3 |
| Write integration tests for payment flow | code-review | 87.3 |
| Debug and fix 6 broken database triggers and constraints | debugging | 90.7 |
| Add file upload with S3 presigned URLs | backend | 87.5 |
| Build REST API from scratch | from-scratch | 94.8 |
| Fix broken GitHub Actions CI pipeline | debugging | 91.8 |
| Implement JWT auth middleware | backend | 68.2 |
| Dockerize Node.js monorepo | full-stack | 86.2 |
| Migrate Express monolith to modular architecture | backend | 94.6 |
| Add Redis caching layer to Express API | backend | 86.6 |
| Add rate limiting middleware | backend | 86.3 |
| Add GraphQL layer over REST API | multi-language | 90.0 |
| Build LLM evaluation harness with structured grading | backend | 81.8 |
| Fix React hydration mismatch | frontend | 84.5 |
| Refactor monolithic handler to CQRS | refactoring | 86.5 |
| Code review: identify security vulns | code-review | 92.5 |
| Write tests for untested legacy Flask service | code-review | 87.5 |
| Add retry logic and dead letter queue to Python task queue | backend | 84.9 |
| Add streaming SSE endpoint for LLM chat | backend | 59.9 |
| Replace console.log with structured logging | refactoring | 89.6 |
| Build terminal UI dashboard | from-scratch | 85.8 |
| Harden insecure Docker setup with 12 vulnerabilities | code-review | 92.2 |
| Find and fix 4 hidden backdoors in Flask app | debugging | 90.3 |
| Add WebSocket real-time updates | full-stack | 87.8 |