Back to models
Qwen3 Coder 30b [Q4_K_M]
LM Studio
262K context<$0.01/M input<$0.01/M output
1161peak 1163
Avg Score
52.1
Avg Cost
$0.01
Score/$
4737.7
Runs
40
Win/Loss/Draw
Scoring Dimensions
Score Distribution
Category ELOs
refactoringexpert
1592frontendhard
1485from-scratcheasy
1474refactoring
1469backendmedium
1309frontendmedium
1260frontend
1247from-scratch
1184backend
1135debugginghard
1122from-scratchhard
1108code-review
1098code-reviewhard
1087debugging
1068backendexpert
1022backendhard
1021debuggingmedium
1015code-reviewmedium
977full-stack
832full-stackhard
821debuggingexpert
765from-scratchexpert
481frontendexpert
131from-scratchmedium
96backendeasy
0All Results
| Task | Category | Score |
|---|---|---|
| Build SaaS admin dashboard from scratch | from-scratch | 55.8 |
| Build production website with auth and members area | frontend | 46.3 |
| Build MCP server for database management | backend | 44.5 |
| Implement transformer inference engine with KV cache | from-scratch | 53.5 |
| Build CLI tool with subcommands and config | from-scratch | 36.3 |
| Implement background job scheduler with persistence | backend | 19.8 |
| Build LLM evaluation harness with structured grading | backend | 44.3 |
| Fix hallucination and context window bugs in RAG agent | backend | 51.0 |
| Build real-time portfolio risk calculator | backend | 41.0 |
| Fix race conditions in order matching engine | backend | 62.5 |
| Build materialized view refresh pipeline for analytics | backend | 46.3 |
| Fix data integrity bugs in denormalized e-commerce schema | debugging | 38.0 |
| Fix deadlocking transaction patterns in Flask app | backend | 37.8 |
| Find and fix 4 hidden backdoors in Flask app | debugging | 70.5 |
| Write complex SQL report with window functions | backend | 61.2 |
| Debug and fix 6 broken database triggers and constraints | debugging | 49.6 |
| Add Redis caching layer to Express API | backend | 56.0 |
| Write tests for untested legacy Flask service | code-review | 18.3 |
| Add Google OAuth2 login to Express app | full-stack | 41.5 |
| Optimize slow Postgres queries in Flask app | backend | 58.7 |
| Add slash commands and moderation to Discord bot | backend | 55.6 |
| Add retry logic and dead letter queue to Python task queue | backend | 51.6 |
| Fix 12 WCAG accessibility violations in checkout form | frontend | 77.9 |
| Fix Node.js stream backpressure causing OOM on large files | backend | 86.2 |
| Add virtual scrolling to table rendering 5000 rows | frontend | 65.2 |
| Build distributed node cluster with gossip protocol | from-scratch | 33.5 |
| Write integration tests for payment flow | code-review | 63.5 |
| Fix auth bypass vulnerability | debugging | 74.5 |
| Implement Stripe webhook handler | backend | 40.0 |
| Zero-downtime schema migration | full-stack | 44.5 |
| Add rate limiting middleware | backend | 18.3 |
| Fix flaky test suite | debugging | 62.5 |
| Refactor monolithic handler to CQRS | refactoring | 65.5 |
| Fix N+1 query in dashboard | backend | 63.5 |
| Fix memory leak in event handler | debugging | 55.1 |
| Code review: identify security vulns | code-review | 53.3 |
| Fix React hydration mismatch | frontend | 67.0 |
| Debug race condition in worker pool | debugging | 58.0 |
| Build terminal UI dashboard | from-scratch | 37.0 |
| Build REST API from scratch | from-scratch | 79.3 |