Back to models
Minimax M2.5
OpenRouter
205K context$0.30/M input$1.20/M output
1358peak 1373
Avg Score
64.7
Avg Cost
$0.09
Score/$
712.3
Runs
65
Win/Loss/Draw
Scoring Dimensions
Score Distribution
Category ELOs
from-scratchexpert
1977frontendhard
1677debugginghard
1595code-reviewhard
1518frontendexpert
1465frontend
1448backendexpert
1427frontendmedium
1426full-stack
1423full-stackhard
1417full-stackmedium
1414debugging
1405backendmedium
1393frontendeasy
1339code-review
1335refactoringmedium
1325backend
1322from-scratch
1307refactoring
1305code-reviewmedium
1285debuggingexpert
1278from-scratcheasy
1249from-scratchhard
1215multi-language
1197backendhard
1163debuggingmedium
1146multi-languagehard
955multi-languageexpert
743backendeasy
582refactoringexpert
387from-scratchmedium
0All Results
| Task | Category | Score |
|---|---|---|
| Port Python CLI to Rust | multi-language | 39.6 |
| Build SaaS admin dashboard from scratch | from-scratch | 53.0 |
| Implement zero-trust API authentication layer | backend | 81.7 |
| Build real-time portfolio risk calculator | backend | 79.0 |
| Build codebase indexer for LLM context windows | from-scratch | 70.1 |
| Code review: identify security vulns | code-review | 81.3 |
| Split 1100-line god file into proper modules | refactoring | 71.5 |
| Find and patch all OWASP Top 10 vulnerabilities | debugging | 65.8 |
| Fix broken responsive layout | frontend | 71.1 |
| Write complex SQL report with window functions | backend | 60.5 |
| Optimize bloated React bundle under 500KB | frontend | 73.2 |
| Implement background job scheduler with persistence | backend | 31.9 |
| Build materialized view refresh pipeline for analytics | backend | 72.6 |
| Optimize slow Postgres queries in Flask app | backend | 69.7 |
| Fix 12 WCAG accessibility violations in checkout form | frontend | 81.6 |
| Implement multi-tenant row-level security in Postgres | backend | 44.8 |
| Fix race conditions in order matching engine | backend | 59.6 |
| Debug race condition in worker pool | debugging | 85.1 |
| Build MCP server for database management | backend | 53.5 |
| Fix Node.js stream backpressure causing OOM on large files | backend | 32.8 |
| Add cursor-based pagination to REST API | backend | 72.0 |
| Fix auth bypass vulnerability | debugging | 89.7 |
| Write integration tests for payment flow | code-review | 73.3 |
| Fix flaky test suite | debugging | 64.5 |
| Add slash commands and moderation to Discord bot | backend | 75.9 |
| Add WebSocket real-time updates | full-stack | 73.3 |
| Replace console.log with structured logging | refactoring | 54.6 |
| Fix hallucination and context window bugs in RAG agent | backend | 45.6 |
| Add GraphQL layer over REST API | multi-language | 63.8 |
| Build REST API from scratch | from-scratch | 74.6 |
| Add Redis caching layer to Express API | backend | 79.8 |
| Remove AI slop and over-engineering from codebase | refactoring | 75.1 |
| Add Google OAuth2 login to Express app | full-stack | 81.2 |
| Convert React app to PWA with offline support | frontend | 80.2 |
| Fix data integrity bugs in denormalized e-commerce schema | debugging | 74.5 |
| Build terminal UI dashboard | from-scratch | 31.6 |
| Fix N+1 query in dashboard | backend | 45.0 |
| Implement Stripe webhook handler | backend | 53.3 |
| Fix broken GitHub Actions CI pipeline | debugging | 75.7 |
| Write tests for untested legacy Flask service | code-review | 38.1 |
| Add virtual scrolling to table rendering 5000 rows | frontend | 40.3 |
| Fix React hydration mismatch | frontend | 78.0 |
| Build CLI tool with subcommands and config | from-scratch | 29.4 |
| Find and fix 4 hidden backdoors in Flask app | debugging | 90.3 |
| Dockerize Node.js monorepo | full-stack | 71.5 |
| Implement JWT auth middleware | backend | 53.9 |
| Implement transformer inference engine with KV cache | from-scratch | 85.4 |
| Build RAG pipeline with vector search | backend | 42.0 |
| Build LLM evaluation harness with structured grading | backend | 43.5 |
| Add i18n with locale routing to Next.js app | full-stack | 68.3 |
| Write Kubernetes manifests for Node.js microservice | full-stack | 82.2 |
| Fix memory leak in event handler | debugging | 81.0 |
| Add streaming SSE endpoint for LLM chat | backend | 77.3 |
| Fix deadlocking transaction patterns in Flask app | backend | 78.0 |
| Add rate limiting middleware | backend | 43.0 |
| Debug and fix 6 broken database triggers and constraints | debugging | 72.2 |
| Harden insecure Docker setup with 12 vulnerabilities | code-review | 68.0 |
| Build production website with auth and members area | frontend | 67.3 |
| Refactor monolithic handler to CQRS | refactoring | 40.6 |
| Add file upload with S3 presigned URLs | backend | 77.3 |
| Zero-downtime schema migration | full-stack | 63.0 |
| Add caching layer to eliminate slow SSR page loads | full-stack | 80.1 |
| Add retry logic and dead letter queue to Python task queue | backend | 74.8 |
| Migrate callback-hell Express app to async/await | refactoring | 62.8 |
| Build distributed node cluster with gossip protocol | from-scratch | 36.6 |