evalsize
How many eval examples do I need? Sample size and power planning for LLM evals, with a calculator that runs in your browser.
Most teams pick an eval size by feel: 100 questions, maybe 500. Then a new prompt scores 2 points higher and nobody knows whether that is real. evalsize answers the planning questions before you spend the API budget:
- How many questions do I need to tell whether model B beats model A?
- How precise is the score I already have?
- Is the difference I measured real, or noise?
- Should I add more questions, or run each question several times?
- My LLM judge makes mistakes. How much does that move the score, and how many answers should I label by hand?
The number most people get wrong
Comparing a 70% model with a 75% model, at the usual 80% power:
| Setup | Questions needed |
|---|---|
| Each model on its own set of questions | 1,251 per model |
| Same questions, models make mistakes independently | 1,254 |
| Same questions, models disagree on 15% of them | 469 |
When both models answer the same questions, only the questions where they disagree tell you which is better. Models often get the same questions right and the same ones wrong, so they usually disagree far less than chance would suggest, and you need far fewer questions. But only if you measure the disagreement rate. Run a small pilot, count the questions where exactly one model is right, and plan with that number.
Try it
In the browser: ai-with-md.github.io/evalsize. Move the sliders, nothing to install.
In Python:
pip install evalsize
No dependencies beyond the standard library. Python 3.9 or newer.
Use
1. How many questions to compare two models?
import evalsize as es
es.examples_to_compare(baseline=0.70, improvement=0.05, disagreement=0.15)
# 469
es.smallest_detectable_improvement(n=300, baseline=0.70, disagreement=0.15)
# 0.062 -> with 300 questions you can reliably detect about 6 points, not less
Leave out disagreement and evalsize assumes the models make mistakes independently, which is the cautious answer. Pass paired=False if the two models answer different questions.
2. How precise is one score?
es.pass_rate_interval(passes=160, n=200)
# Pass rate 80.0% (160 of 200). 95% confidence interval: 73.9% to 85.0%.
es.examples_for_margin(margin=0.03, pass_rate=0.80)
# 682 questions for plus or minus 3 points
3. Is B really better than A?
result = es.compare_results(a_passed, b_passed) # two lists of True/False, same question order
print(result)
# B minus A: +5.3% over 300 shared questions (95% interval +1.2% to +9.4%, p = 0.0166).
# B looks better than A. The models disagreed on 40 questions.
Or from counts: es.compare_counts(n=300, only_a_right=12, only_b_right=28).
4. More questions, or more runs per question?
If a model gives different answers on different runs, rerunning each question averages out that randomness. It cannot fix the other source of noise: which questions you picked.
share = es.question_share(pilot_runs) # one row per question, one 0/1 per run
es.effective_examples(n_questions=200, runs_per_question=5, question_share=share)
# with share 0.6: worth 294 single-run questions, and no number of reruns can beat 333
A deterministic model has a question share of 1, and reruns add nothing. Per API call, adding questions always buys more precision than adding runs, so reruns make most sense when you have run out of good questions.
5. Can I trust my LLM judge?
A judge that passes some bad answers or fails some good ones does not just add noise. It moves the score in one direction. Label a random sample by hand, measure the judge, and correct:
check = es.judge_agreement(human_labels, judge_labels)
print(check)
# The judge agreed with humans on 87.5% of 200 labels. It passed 95.0% of answers
# humans passed and failed 70.0% of answers humans failed.
es.correct_judge_rate(judge_rate=0.82, n_judged=1000,
sensitivity=check.sensitivity, specificity=check.specificity,
human_passes=check.human_passes, human_fails=check.human_fails)
# The judge says 82.0%. Corrected for the judge's mistakes: 80.0% (95% interval 73.2% to 86.8%).
es.labels_to_check_judge(margin=0.05, pass_rate=0.80)
# how many answers to label by hand before you start
Command line
evalsize compare --baseline 0.7 --improvement 0.05 --disagreement 0.15
evalsize detect --baseline 0.7 --n 300 --disagreement 0.15
evalsize margin --rate 0.8 --margin 0.03
evalsize diff --n 300 --only-a 12 --only-b 28
evalsize reruns --n 200 --share 0.6
evalsize judge --judge-rate 0.82 --sensitivity 0.95 --specificity 0.7 --human-passes 140 --human-fails 60
How the numbers are checked
Formulas are easy to get subtly wrong, so every one is tested against simulation. The test suite runs thousands of fake evals with known true pass rates and checks that the promises hold: the sample sizes deliver their stated power, the intervals cover the truth 95% of the time, the false alarm rate stays at 5%, and the rerun and judge corrections match what the simulations show. See tests/test_simulation.py.
How it compares
- evalstats analyzes results after you run an eval, with many tests and judge-bias corrections. evalsize is mostly about planning before you run: how many questions, how many runs, how many human labels. They work well together.
- General power calculators (statsmodels, G*Power, online calculators) handle two separate groups well, but rarely the paired case with a disagreement rate, which is how most LLM evals are run, and they say nothing about reruns or imperfect judges.
Methods
| Question | Method |
|---|---|
| Precision of one score | Wilson score interval |
| Comparing two models, planning | McNemar sample size formula (Connor, 1987); two-proportion formula when unpaired |
| Comparing two models, analysis | Exact McNemar test, Agresti and Min (2005) interval for the paired difference |
| Reruns | Intraclass correlation (one-way analysis of variance estimator) and the design effect |
| Imperfect judges | Rogan and Gladen (1978) estimator with a delta method interval that includes the uncertainty in the judge's measured error rates |
Everything here is for pass/fail scores, which is how most evals are reported. Planning for scores on a scale (1 to 5, or 0 to 1) is a likely next step.
Development
python -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"
pytest
The calculator is a marimo notebook in app/calculator.py. To run it locally: pip install marimo matplotlib, then marimo run app/calculator.py. It is published to GitHub Pages as a WebAssembly app on every push to main.
License
MIT
Metadata
Release files for evalsize 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| evalsize-0.1.0.tar.gz | 19.4 kB | With provenance | Details for evalsize-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| evalsize-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for evalsize-0.1.0-py3-none-any.whl |
Total release size: 36.0 kB
Release files / evalsize-0.1.0.tar.gz
| Download URL | evalsize-0.1.0.tar.gz |
|---|---|
| Size | 19.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
4643cfc31e427ef61201af59eb207ae1d3d0eb20cc45f7a45095e928a35b9414
|
|
BLAKE2b-256 checksum How to use checksums |
83bc977790c87f9020e422a3e56e004a74a28674dab0c4f8f9fa83509cb0443a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 13, 2026.
Transparency logRelease files / evalsize-0.1.0-py3-none-any.whl
| Download URL | evalsize-0.1.0-py3-none-any.whl |
|---|---|
| Size | 16.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
d2af629f4d201885ad04858b412d8a5452be4de1a0db41ffab2a3a6df0550a53
|
|
BLAKE2b-256 checksum How to use checksums |
d6062770b68a05e9876dbbc2c85dd471ec668105bb3345379dd4abd0be7672a5
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 13, 2026.
Transparency logSecurity for evalsize 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
Both files in this release have been uploaded with provenance metadata.
Attestation for evalsize-0.1.0.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 13, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.