PrototypeCommon
ianarawjo/evalstats
Statistical inference for AI evaluations, from model comparisons to corrections for LLM judge bias, optimized for small sample sizes. All defaults battle-tested in Monte Carlo simulations.
- Owner
- ianarawjo (personal account)
- Stars
- Stars: 131
- Forks
- Forks: 3
- Language
- Python
- License
- None
- Created
- 2026
- Topics
- ai-evaluationai-evaluation-toolsai-statisticsbenchmarkingprompt-engineeringprompt-evaluationstatistical-analysis
- Tier
- Prototype (100 to 249 ★) What this tier means
More repos by ianarawjo
All 2 repos by ianarawjo- ianarawjo/ChainForgeStars: 3,040TypeScriptRC
Nearby in Python
All Python repos- yurenpai/mc-points-stewardStars: 131PythonPrototype
- galilai-group/prh-proofStars: 131PythonPrototype
- yesterdayfuture/confessStars: 131PythonPrototype
- jerem/psdparseStars: 131PythonPrototype
- davepeck/game-of-goStars: 131PythonPrototype
- brendano/tsvutilsStars: 131PythonPrototype