Back to models
Minimax M2.5 [Q4_K_XL]
LM Studio
197K context<$0.01/M input<$0.01/M output
1372peak 1373
Avg Score
63.9
Avg Cost
$0.03
Score/$
2128.9
Runs
39
Win/Loss/Draw
Scoring Dimensions
Score Distribution
Category ELOs
from-scratcheasy
2230frontendexpert
2135multi-languagehard
1926frontendhard
1795frontend
1631code-reviewmedium
1631backendeasy
1627multi-language
1625frontendmedium
1568debugginghard
1474backendhard
1367from-scratch
1362code-review
1358backendmedium
1339backend
1326debugging
1295refactoring
1289from-scratchhard
1205full-stack
1204full-stackhard
1196backendexpert
1126from-scratchmedium
1120from-scratchexpert
985debuggingexpert
974refactoringexpert
963debuggingmedium
772code-reviewhard
85All Results
| Task | Category | Score |
|---|---|---|
| Implement background job scheduler with persistence | backend | 37.0 |
| Build MCP server for database management | backend | 47.0 |
| Implement transformer inference engine with KV cache | from-scratch | 67.7 |
| Build CLI tool with subcommands and config | from-scratch | 41.5 |
| Build production website with auth and members area | frontend | 75.5 |
| Build SaaS admin dashboard from scratch | from-scratch | 63.2 |
| Fix data integrity bugs in denormalized e-commerce schema | debugging | 52.9 |
| Build terminal UI dashboard | from-scratch | 55.6 |
| Build real-time portfolio risk calculator | backend | 21.8 |
| Write tests for untested legacy Flask service | code-review | 65.9 |
| Add slash commands and moderation to Discord bot | backend | 57.1 |
| Fix deadlocking transaction patterns in Flask app | backend | 68.5 |
| Implement Stripe webhook handler | backend | 61.2 |
| Build REST API from scratch | from-scratch | 90.1 |
| Fix N+1 query in dashboard | backend | 64.5 |
| Fix 12 WCAG accessibility violations in checkout form | frontend | 82.9 |
| Add retry logic and dead letter queue to Python task queue | backend | 63.5 |
| Fix auth bypass vulnerability | debugging | 93.7 |
| Refactor monolithic handler to CQRS | refactoring | 51.8 |
| Fix hallucination and context window bugs in RAG agent | backend | 67.7 |
| Fix race conditions in order matching engine | backend | 66.5 |
| Debug and fix 6 broken database triggers and constraints | debugging | 58.4 |
| Add Redis caching layer to Express API | backend | 75.8 |
| Fix flaky test suite | debugging | 44.8 |
| Optimize slow Postgres queries in Flask app | backend | 81.7 |
| Fix Node.js stream backpressure causing OOM on large files | backend | 81.8 |
| Fix React hydration mismatch | frontend | 77.7 |
| Build distributed node cluster with gossip protocol | from-scratch | 30.5 |
| Find and fix 4 hidden backdoors in Flask app | debugging | 92.5 |
| Debug race condition in worker pool | debugging | 68.7 |
| Write integration tests for payment flow | code-review | 39.5 |
| Add virtual scrolling to table rendering 5000 rows | frontend | 79.0 |
| Build LLM evaluation harness with structured grading | backend | 41.6 |
| Fix memory leak in event handler | debugging | 61.1 |
| Write complex SQL report with window functions | backend | 78.5 |
| Add rate limiting middleware | backend | 75.4 |
| Add cursor-based pagination to REST API | backend | 67.6 |
| Zero-downtime schema migration | full-stack | 62.4 |
| Add GraphQL layer over REST API | multi-language | 80.5 |