# evalci: A Python Library for Statistically Rigorous Comparison of Language Model Evaluations

arXiv: https://arxiv.org/abs/2607.04429 · HTML: https://mlsanity.com/paper/2607.04429/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 16 references that are in the map.
- First posted on arXiv 5 Jul 2026.

## Builds on (most cited first, 4 of 4)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations](https://mlsanity.com/paper/2411.00640/) (2024)
- [With Little Power Comes Great Responsibility](https://mlsanity.com/paper/2010.06595/) (2020)

## Built on by (most cited first, 1 of 1)

- [Anytime-Valid LLM Leaderboards via Benchmark-weighted and Block-Factorized e-Processes](https://mlsanity.com/paper/2609.32248/) (2026)

## Abstract (arXiv)

The dominant practice in language model evaluation is to report a single accuracy number per model and declare the higher one better, without testing whether the gap could plausibly be sampling noise. On benchmarks of a few thousand items, and under temperature sampling where a model can differ from itself run to run by more than the reported gap between models, this practice routinely overstates confidence in headline claims. The statistical machinery to fix this -- confidence intervals, paired significance tests, power analysis, clustered standard errors, multiple-comparison correction -- is well established, but no standard, pip-installable tool packages it in the shape an evaluation actually takes: a per-item results table. We present evalci, a pure-Python library (numpy/scipy/pandas only) that turns a per-item results table into a publication-ready claim -- e.g., "Model A beats Model B, Delta=3.1 pts, 95% CI [1.2, 5.0], paired permutation p=0.002, n=1,319" -- in one function call, with adapters for lm-evaluation-harness and HELM output. Every routine is validated against an independent reference (statsmodels, or brute-force exact enumeration) rather than only against itself. As a case study, we re-analyze a public comparison of nine language models' MMLU accuracy and find that 3 of the 8 adjacent leaderboard-rank gaps are not statistically significant after correcting for the 36 pairwise comparisons the ranking implies. evalci is available at https://pypi.org/project/evalci/ (source: https://github.com/Shreyaskc/evalci, DOI: https://doi.org/10.5281/zenodo.21201815)