# ianarawjo/evalstats

<https://repo.masters-masters.com/en/repos/ianarawjo/evalstats>

[Home](https://repo.masters-masters.com/en) › [ianarawjo](https://repo.masters-masters.com/en/owners/ianarawjo) › [evalstats](https://repo.masters-masters.com/en/repos/ianarawjo/evalstats)

ianarawjo/evalstats has 131 stars on GitHub. Its RepoMasters card: Prototype tier. Statistical inference for AI evaluations, from model comparisons to…

| Field | Value |
| --- | --- |
| Owner | [ianarawjo](https://repo.masters-masters.com/en/owners/ianarawjo) |
| Stars | 131 |
| Forks | 3 |
| Language | [Python](https://repo.masters-masters.com/en/languages/python) |
| License | None |
| Created | 2026 |
| Topics | ai-evaluation, ai-evaluation-tools, ai-statistics, benchmarking, prompt-engineering, prompt-evaluation, statistical-analysis |
| Tier | [Prototype (100 to 249 ★)](https://repo.masters-masters.com/en/ranks/rush) |
| View on GitHub | [ianarawjo/evalstats](https://github.com/ianarawjo/evalstats) |

## Repository

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.

The tier for repos with 100 to 249 ★. Published odds per card pulled: 70%. Rarity: Common.

## More repos by ianarawjo

- [ianarawjo/ChainForge · ★ 3,041 · TypeScript · RC](https://repo.masters-masters.com/en/repos/ianarawjo/ChainForge)

## Nearby in Python

- [rzc156/dreamforge · ★ 131 · Python · Prototype](https://repo.masters-masters.com/en/repos/rzc156/dreamforge)
- [yurenpai/mc-points-steward · ★ 131 · Python · Prototype](https://repo.masters-masters.com/en/repos/yurenpai/mc-points-steward)
- [yesterdayfuture/confess · ★ 131 · Python · Prototype](https://repo.masters-masters.com/en/repos/yesterdayfuture/confess)
- [jerem/psdparse · ★ 131 · Python · Prototype](https://repo.masters-masters.com/en/repos/jerem/psdparse)
- [davepeck/game-of-go · ★ 131 · Python · Prototype](https://repo.masters-masters.com/en/repos/davepeck/game-of-go)
- [brendano/tsvutils · ★ 131 · Python · Prototype](https://repo.masters-masters.com/en/repos/brendano/tsvutils)

---
Data: GitHub · Illustration drawn by RepoMasters from the repo’s ID and its language color.