Back to models
GLM 4.7 [Q4_K_XL]
LM Studio
200K context$0.60/M input$2.20/M output
1399peak 1589
Avg Score
71.2
Avg Cost
$0.04
Score/$
2021.2
Runs
41
Win/Loss/Draw
Scoring Dimensions
Score Distribution
Category ELOs
from-scratchexpert
2076from-scratcheasy
1781frontendexpert
1735backendeasy
1691from-scratchmedium
1644from-scratch
1589multi-languagehard
1551from-scratchhard
1495frontendhard
1483frontend
1451debugginghard
1436multi-language
1423full-stack
1396backendmedium
1396refactoring
1393full-stackhard
1393frontendmedium
1389backend
1383backendhard
1346backendexpert
1346refactoringexpert
1344debugging
1315code-reviewmedium
1178debuggingmedium
1178code-review
1132debuggingexpert
1000code-reviewhard
309All Results
| Task | Category | Score |
|---|---|---|
| Build production website with auth and members area | frontend | 72.5 |
| Fix data integrity bugs in denormalized e-commerce schema | debugging | 63.4 |
| Build LLM evaluation harness with structured grading | backend | 74.4 |
| Build MCP server for database management | backend | 57.4 |
| Implement background job scheduler with persistence | backend | 73.1 |
| Fix hallucination and context window bugs in RAG agent | backend | 64.4 |
| Build SaaS admin dashboard from scratch | from-scratch | 73.6 |
| Implement transformer inference engine with KV cache | from-scratch | 87.5 |
| Build real-time portfolio risk calculator | backend | 58.9 |
| Build CLI tool with subcommands and config | from-scratch | 57.2 |
| Fix race conditions in order matching engine | backend | 80.1 |
| Fix deadlocking transaction patterns in Flask app | backend | 62.4 |
| Debug and fix 6 broken database triggers and constraints | debugging | 68.1 |
| Write complex SQL report with window functions | backend | 71.5 |
| Find and fix 4 hidden backdoors in Flask app | debugging | 88.5 |
| Add Redis caching layer to Express API | backend | 50.9 |
| Write tests for untested legacy Flask service | code-review | 54.5 |
| Add Google OAuth2 login to Express app | full-stack | 79.8 |
| Optimize slow Postgres queries in Flask app | backend | 81.2 |
| Add slash commands and moderation to Discord bot | backend | 68.7 |
| Add retry logic and dead letter queue to Python task queue | backend | 51.2 |
| Fix Node.js stream backpressure causing OOM on large files | backend | 89.8 |
| Add virtual scrolling to table rendering 5000 rows | frontend | 82.2 |
| Fix 12 WCAG accessibility violations in checkout form | frontend | 80.0 |
| Build distributed node cluster with gossip protocol | from-scratch | 74.5 |
| Fix auth bypass vulnerability | debugging | 88.5 |
| Add GraphQL layer over REST API | multi-language | 77.5 |
| Write integration tests for payment flow | code-review | 58.5 |
| Zero-downtime schema migration | full-stack | 61.8 |
| Add rate limiting middleware | backend | 79.0 |
| Implement Stripe webhook handler | backend | 70.5 |
| Fix flaky test suite | debugging | 73.9 |
| Add cursor-based pagination to REST API | backend | 82.9 |
| Fix N+1 query in dashboard | backend | 75.8 |
| Fix memory leak in event handler | debugging | 61.1 |
| Code review: identify security vulns | code-review | 49.0 |
| Refactor monolithic handler to CQRS | refactoring | 68.8 |
| Debug race condition in worker pool | debugging | 85.0 |
| Fix React hydration mismatch | frontend | 67.5 |
| Build terminal UI dashboard | from-scratch | 68.6 |
| Build REST API from scratch | from-scratch | 87.0 |