Back to models
Minimax M3
OpenRouter
1049K context$0.30/M input$1.20/M output
1701peak 1840
Avg Score
83.9
Avg Cost
$0.15
Score/$
577.7
Runs
70
Win/Loss/Draw
Scoring Dimensions
Score Distribution
Category ELOs
multi-languageexpert
2867refactoringexpert
2629code-reviewhard
2314from-scratchmedium
2213multi-languagehard
2139frontendexpert
2117frontendeasy
2031multi-language
1996backendeasy
1976refactoring
1896debuggingexpert
1857refactoringmedium
1847backendexpert
1833frontendmedium
1818from-scratchhard
1803code-review
1783full-stackhard
1764code-reviewmedium
1745full-stack
1703frontend
1703backend
1700backendmaster
1692from-scratch
1687backendhard
1686from-scratchexpert
1685backendmedium
1642full-stackmedium
1639debugging
1625debugginghard
1551from-scratcheasy
1523debuggingmedium
1521frontendmaster
1518frontendhard
1398All Results
| Task | Category | Score |
|---|---|---|
| Build 3D browser game with physics and multiplayer sync | frontend | 70.7 |
| Add streaming SSE endpoint for LLM chat | backend | 90.4 |
| Fix memory leak in event handler | debugging | 72.7 |
| Port Python CLI to Rust | multi-language | 88.6 |
| Implement zero-trust API authentication layer | backend | 83.4 |
| Build RAG pipeline with vector search | backend | 86.0 |
| Fix N+1 query in dashboard | backend | 75.5 |
| Migrate Express monolith to modular architecture | backend | 87.3 |
| Add i18n with locale routing to Next.js app | full-stack | 80.7 |
| Fix and extend Chrome browser extension | frontend | 68.0 |
| Build interactive data visualization dashboard | frontend | 79.5 |
| Add WebSocket real-time updates | full-stack | 86.3 |
| Implement multi-tenant row-level security in Postgres | backend | 87.3 |
| Fix broken responsive layout | frontend | 83.6 |
| Build LLM evaluation harness with structured grading | backend | 75.1 |
| Build codebase indexer for LLM context windows | from-scratch | 73.2 |
| Optimize slow Postgres queries in Flask app | backend | 74.9 |
| Fix flaky test suite | debugging | 72.8 |
| Fix 12 WCAG accessibility violations in checkout form | frontend | 78.5 |
| Split 1100-line god file into proper modules | refactoring | 86.5 |
| Write integration tests for payment flow | code-review | 88.6 |
| Build production website with auth and members area | frontend | 78.4 |
| Build terminal UI dashboard | from-scratch | 79.0 |
| Add virtual scrolling to table rendering 5000 rows | frontend | 87.3 |
| Build SaaS admin dashboard from scratch | from-scratch | 72.8 |
| Refactor monolithic handler to CQRS | refactoring | 91.5 |
| Convert React app to PWA with offline support | frontend | 81.6 |
| Optimize bloated React bundle under 500KB | frontend | 84.7 |
| Write tests for untested legacy Flask service | code-review | 89.9 |
| Harden insecure Docker setup with 12 vulnerabilities | code-review | 92.3 |
| Fix Node.js stream backpressure causing OOM on large files | backend | 82.1 |
| Fix hallucination and context window bugs in RAG agent | backend | 74.8 |
| Add Redis caching layer to Express API | backend | 90.3 |
| Implement transformer inference engine with KV cache | from-scratch | 81.0 |
| Find and fix 4 hidden backdoors in Flask app | debugging | 88.7 |
| Write complex SQL report with window functions | backend | 90.9 |
| Add retry logic and dead letter queue to Python task queue | backend | 80.8 |
| Remove AI slop and over-engineering from codebase | refactoring | 87.7 |
| Write Kubernetes manifests for Node.js microservice | full-stack | 90.8 |
| Fix deadlocking transaction patterns in Flask app | backend | 88.3 |
| Build distributed node cluster with gossip protocol | from-scratch | 83.3 |
| Add cursor-based pagination to REST API | backend | 78.3 |
| Fix data integrity bugs in denormalized e-commerce schema | debugging | 91.5 |
| Implement background job scheduler with persistence | backend | 83.5 |
| Debug and fix 6 broken database triggers and constraints | debugging | 90.3 |
| Fix auth bypass vulnerability | debugging | 91.0 |
| Build CLI tool with subcommands and config | from-scratch | 83.0 |
| Build MCP server for database management | backend | 87.3 |
| Find and patch all OWASP Top 10 vulnerabilities | debugging | 89.1 |
| Fix broken GitHub Actions CI pipeline | debugging | 94.4 |
| Implement JWT auth middleware | backend | 90.0 |
| Add rate limiting middleware | backend | 84.4 |
| Zero-downtime schema migration | full-stack | 84.4 |
| Build materialized view refresh pipeline for analytics | backend | 76.8 |
| Add file upload with S3 presigned URLs | backend | 81.3 |
| Add Google OAuth2 login to Express app | full-stack | 81.6 |
| Add caching layer to eliminate slow SSR page loads | full-stack | 82.8 |
| Build real-time portfolio risk calculator | backend | 86.2 |
| Dockerize Node.js monorepo | full-stack | 80.5 |
| Add slash commands and moderation to Discord bot | backend | 78.9 |
| Fix React hydration mismatch | frontend | 89.1 |
| Fix race conditions in order matching engine | backend | 90.3 |
| Replace console.log with structured logging | refactoring | 92.0 |
| Migrate callback-hell Express app to async/await | refactoring | 90.8 |
| Build multi-tool LLM agent runtime | backend | 84.9 |
| Implement Stripe webhook handler | backend | 85.7 |
| Add GraphQL layer over REST API | multi-language | 87.0 |
| Code review: identify security vulns | code-review | 79.3 |
| Build REST API from scratch | from-scratch | 84.1 |
| Debug race condition in worker pool | debugging | 89.7 |