Back to models
Deepseek V3.2
OpenRouter
164K context$0.25/M input$0.38/M output
1360peak 1377
Avg Score
64.3
Avg Cost
$0.04
Score/$
1765.2
Runs
65
Win/Loss/Draw
Scoring Dimensions
Score Distribution
Category ELOs
multi-languageexpert
1521code-reviewmedium
1519debuggingmedium
1473debugginghard
1464code-review
1456frontendhard
1435frontend
1406debugging
1403frontendexpert
1403frontendeasy
1398frontendmedium
1394backendhard
1386backendexpert
1369backend
1368backendmedium
1361debuggingexpert
1325refactoringmedium
1296refactoring
1278from-scratch
1273from-scratcheasy
1272full-stack
1255full-stackmedium
1241multi-language
1235full-stackhard
1235from-scratchhard
1198code-reviewhard
1181from-scratchmedium
1164from-scratchexpert
959backendeasy
582refactoringexpert
328multi-languagehard
0All Results
| Task | Category | Score |
|---|---|---|
| Build distributed node cluster with gossip protocol | from-scratch | 38.7 |
| Write complex SQL report with window functions | backend | 70.6 |
| Find and fix 4 hidden backdoors in Flask app | debugging | 72.5 |
| Convert React app to PWA with offline support | frontend | 63.6 |
| Debug and fix 6 broken database triggers and constraints | debugging | 72.5 |
| Add retry logic and dead letter queue to Python task queue | backend | 38.0 |
| Implement zero-trust API authentication layer | backend | 76.8 |
| Implement multi-tenant row-level security in Postgres | backend | 60.0 |
| Implement background job scheduler with persistence | backend | 62.0 |
| Add file upload with S3 presigned URLs | backend | 40.0 |
| Optimize slow Postgres queries in Flask app | backend | 84.8 |
| Add i18n with locale routing to Next.js app | full-stack | 65.8 |
| Find and patch all OWASP Top 10 vulnerabilities | debugging | 67.9 |
| Build real-time portfolio risk calculator | backend | 52.9 |
| Fix memory leak in event handler | debugging | 39.3 |
| Remove AI slop and over-engineering from codebase | refactoring | 79.1 |
| Fix broken GitHub Actions CI pipeline | debugging | 90.8 |
| Add Redis caching layer to Express API | backend | 66.2 |
| Add Google OAuth2 login to Express app | full-stack | 8.6 |
| Add GraphQL layer over REST API | multi-language | 33.3 |
| Add streaming SSE endpoint for LLM chat | backend | 84.0 |
| Fix auth bypass vulnerability | debugging | 95.0 |
| Migrate callback-hell Express app to async/await | refactoring | 58.7 |
| Port Python CLI to Rust | multi-language | 54.3 |
| Build materialized view refresh pipeline for analytics | backend | 62.9 |
| Build RAG pipeline with vector search | backend | 51.3 |
| Code review: identify security vulns | code-review | 83.8 |
| Add WebSocket real-time updates | full-stack | 75.3 |
| Optimize bloated React bundle under 500KB | frontend | 68.5 |
| Fix broken responsive layout | frontend | 72.0 |
| Implement JWT auth middleware | backend | 69.8 |
| Split 1100-line god file into proper modules | refactoring | 75.9 |
| Dockerize Node.js monorepo | full-stack | 67.3 |
| Write Kubernetes manifests for Node.js microservice | full-stack | 71.5 |
| Add caching layer to eliminate slow SSR page loads | full-stack | 78.5 |
| Build codebase indexer for LLM context windows | from-scratch | 27.0 |
| Harden insecure Docker setup with 12 vulnerabilities | code-review | 79.5 |
| Replace console.log with structured logging | refactoring | 40.8 |
| Add rate limiting middleware | backend | 43.1 |
| Build production website with auth and members area | frontend | 65.7 |
| Build SaaS admin dashboard from scratch | from-scratch | 65.0 |
| Fix hallucination and context window bugs in RAG agent | backend | 53.6 |
| Build LLM evaluation harness with structured grading | backend | 64.2 |
| Build MCP server for database management | backend | 81.8 |
| Build CLI tool with subcommands and config | from-scratch | 53.8 |
| Implement transformer inference engine with KV cache | from-scratch | 68.9 |
| Fix race conditions in order matching engine | backend | 81.5 |
| Fix data integrity bugs in denormalized e-commerce schema | debugging | 76.9 |
| Write tests for untested legacy Flask service | code-review | 56.9 |
| Fix deadlocking transaction patterns in Flask app | backend | 47.0 |
| Write integration tests for payment flow | code-review | 68.1 |
| Fix 12 WCAG accessibility violations in checkout form | frontend | 77.3 |
| Add slash commands and moderation to Discord bot | backend | 63.5 |
| Fix Node.js stream backpressure causing OOM on large files | backend | 80.8 |
| Add virtual scrolling to table rendering 5000 rows | frontend | 72.6 |
| Add cursor-based pagination to REST API | backend | 85.9 |
| Build terminal UI dashboard | from-scratch | 59.7 |
| Zero-downtime schema migration | full-stack | 63.1 |
| Refactor monolithic handler to CQRS | refactoring | 40.0 |
| Implement Stripe webhook handler | backend | 53.5 |
| Fix flaky test suite | debugging | 58.0 |
| Build REST API from scratch | from-scratch | 76.3 |
| Fix React hydration mismatch | frontend | 80.3 |
| Fix N+1 query in dashboard | backend | 53.9 |
| Debug race condition in worker pool | debugging | 90.5 |