Overview
What this challenge is about.
Audit an LLM benchmark for data contamination and label quality, re-label 100 items with a peer, and report findings. Earn a verifiable certificate.
The scenario
The nonprofit (around 40 researchers, foundation-funded) ships independent audits as one of its core public goods and is building a track record of constructive engagement with major benchmark maintainers.
The Brief
What you'll do, and what you'll demonstrate.
Audit one prominent open LLM benchmark for validity threats and publish a structured, citable report with recommendations.
Earning criteria — what you'll demonstrate
- Identify the main validity threats to LLM benchmarks
- Run a small structured re-labeling exercise with kappa statistics
- Detect plausible data contamination paths in a public benchmark
- Write a constructive audit report engineers will actually act on
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
AI Measurement and Evaluation
Master · Responsible Ai
Strong alignment
This challenge maps to AI Measurement and Evaluation at the Master level. It sharpens the same practical skills your coursework expects — but in a real industry context with actual constraints and deliverables.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
- Benchmark Evaluation
Apply benchmark evaluation to solve real industry problems and demonstrate production-level capability.
- Data Contamination Analysis
Apply data contamination analysis to solve real industry problems and demonstrate production-level capability.
- Annotation Methodology
Apply annotation methodology to solve real industry problems and demonstrate production-level capability.
- Inter Annotator Agreement
Apply inter annotator agreement to solve real industry problems and demonstrate production-level capability.
- Research Writing
Apply research writing to solve real industry problems and demonstrate production-level capability.
- Llm Evaluation
Apply llm evaluation to solve real industry problems and demonstrate production-level capability.
Careers
Career paths this challenge builds toward
Completing this challenge demonstrates skills that transfer directly to these roles:
AI Safety Researcher
Independent benchmark audits with proper kappa statistics are a recognizable AI safety research contribution and a direct hiring signal.
This challenge sharpens
- benchmark-evaluation
- data-contamination-analysis
- llm-evaluation
Research Scientist
Designing a re-labeling exercise with inter-annotator statistics is the research scientist's first-week deliverable inside an eval-focused lab.
This challenge sharpens
- annotation-methodology
- inter-annotator-agreement
- research-writing
ML Researcher
Understanding benchmark validity threats is foundational for any ML researcher choosing what to optimize against.
This challenge sharpens
- benchmark-evaluation
- llm-evaluation
- research-writing