Back to models
Trinity Large Preview:free
OpenRouter
131K context<$0.01/M input<$0.01/M output
1266peak 1413
Avg Score
55.5
Avg Cost
—
Score/$
—
Runs
65
Win/Loss/Draw
Scoring Dimensions
Score Distribution
Category ELOs
from-scratchexpert
1732frontendhard
1677debuggingmedium
1668debuggingexpert
1651debugging
1478refactoringmedium
1348backendmedium
1334full-stackhard
1332full-stack
1326refactoring
1317full-stackmedium
1295debugginghard
1249frontend
1235code-reviewmedium
1221frontendmedium
1210from-scratcheasy
1208from-scratch
1200backend
1190code-review
1177backendexpert
1093backendhard
1051from-scratchmedium
992from-scratchhard
959multi-language
810frontendexpert
597code-reviewhard
309refactoringexpert
300backendeasy
209multi-languageexpert
63frontendeasy
37multi-languagehard
0All Results
| Task | Category | Score |
|---|---|---|
| Implement zero-trust API authentication layer | backend | 28.0 |
| Optimize bloated React bundle under 500KB | frontend | 25.5 |
| Implement multi-tenant row-level security in Postgres | backend | 28.0 |
| Add streaming SSE endpoint for LLM chat | backend | 45.0 |
| Fix deadlocking transaction patterns in Flask app | backend | 28.0 |
| Debug race condition in worker pool | debugging | 28.0 |
| Split 1100-line god file into proper modules | refactoring | 28.0 |
| Fix memory leak in event handler | debugging | 69.0 |
| Add GraphQL layer over REST API | multi-language | 52.8 |
| Implement background job scheduler with persistence | backend | 44.5 |
| Fix auth bypass vulnerability | debugging | 86.5 |
| Build distributed node cluster with gossip protocol | from-scratch | 33.0 |
| Write tests for untested legacy Flask service | code-review | 25.8 |
| Implement Stripe webhook handler | backend | 47.0 |
| Fix N+1 query in dashboard | backend | 50.0 |
| Fix broken GitHub Actions CI pipeline | debugging | 88.5 |
| Add i18n with locale routing to Next.js app | full-stack | 28.0 |
| Migrate callback-hell Express app to async/await | refactoring | 22.0 |
| Build RAG pipeline with vector search | backend | 45.3 |
| Fix broken responsive layout | frontend | 48.5 |
| Fix 12 WCAG accessibility violations in checkout form | frontend | 84.1 |
| Add Google OAuth2 login to Express app | full-stack | 50.4 |
| Build MCP server for database management | backend | 48.5 |
| Fix hallucination and context window bugs in RAG agent | backend | 50.0 |
| Fix race conditions in order matching engine | backend | 60.9 |
| Build SaaS admin dashboard from scratch | from-scratch | 50.3 |
| Build CLI tool with subcommands and config | from-scratch | 50.0 |
| Find and fix 4 hidden backdoors in Flask app | debugging | 55.0 |
| Add retry logic and dead letter queue to Python task queue | backend | 77.4 |
| Write Kubernetes manifests for Node.js microservice | full-stack | 82.9 |
| Dockerize Node.js monorepo | full-stack | 68.8 |
| Build materialized view refresh pipeline for analytics | backend | 50.4 |
| Build REST API from scratch | from-scratch | 57.5 |
| Add virtual scrolling to table rendering 5000 rows | frontend | 46.1 |
| Refactor monolithic handler to CQRS | refactoring | 49.8 |
| Add file upload with S3 presigned URLs | backend | 48.5 |
| Harden insecure Docker setup with 12 vulnerabilities | code-review | 81.3 |
| Convert React app to PWA with offline support | frontend | 80.8 |
| Build real-time portfolio risk calculator | backend | 47.3 |
| Add cursor-based pagination to REST API | backend | 52.8 |
| Write complex SQL report with window functions | backend | 57.5 |
| Replace console.log with structured logging | refactoring | 82.5 |
| Find and patch all OWASP Top 10 vulnerabilities | debugging | 71.7 |
| Implement transformer inference engine with KV cache | from-scratch | 81.7 |
| Write integration tests for payment flow | code-review | 35.9 |
| Build LLM evaluation harness with structured grading | backend | 56.8 |
| Build production website with auth and members area | frontend | 54.3 |
| Fix data integrity bugs in denormalized e-commerce schema | debugging | 87.3 |
| Debug and fix 6 broken database triggers and constraints | debugging | 90.8 |
| Port Python CLI to Rust | multi-language | 29.3 |
| Add slash commands and moderation to Discord bot | backend | 78.2 |
| Fix flaky test suite | debugging | 86.7 |
| Add rate limiting middleware | backend | 48.5 |
| Fix React hydration mismatch | frontend | 47.0 |
| Zero-downtime schema migration | full-stack | 86.5 |
| Add caching layer to eliminate slow SSR page loads | full-stack | 76.5 |
| Build codebase indexer for LLM context windows | from-scratch | 36.5 |
| Add Redis caching layer to Express API | backend | 43.5 |
| Implement JWT auth middleware | backend | 53.0 |
| Code review: identify security vulns | code-review | 66.9 |
| Remove AI slop and over-engineering from codebase | refactoring | 86.7 |
| Build terminal UI dashboard | from-scratch | 58.5 |
| Add WebSocket real-time updates | full-stack | 53.3 |
| Optimize slow Postgres queries in Flask app | backend | 51.3 |
| Fix Node.js stream backpressure causing OOM on large files | backend | 41.5 |