evalproof
Treat LLM evaluation as measurement. Calibrate the judge, correct its pass rate, and gate CI on regressions that are real rather than noise.
Try it in the browser: evalproof.streamlit.app. Check whether a drop between two runs is real, or replay the run below and read the twelve answers that changed. It runs this repository's code; after a quiet spell it takes about half a minute to wake.
An LLM judge is a classifier with error rates. If it passes bad answers at rate FPR and
good answers at rate TPR, its pass rate converges to FPR + (TPR − FPR) · p, not to the
true rate p. That is classify-and-count, and it is biased the way any classifier's count
is — the effect is worked through with a seeded simulation in
The classifier was 95% accurate. The trend it counted was a third too flat
(lab).
evalproof:
- measures the judge against a small gold-labelled sample — confusion matrix, TPR, FPR, Cohen's κ;
- corrects its pass rate with adjusted classify-and-count and prediction-powered inference, each with a confidence interval;
- compares runs on paired cases — exact McNemar for pass/fail, paired bootstrap for scores;
- gates CI only when a drop is both larger than your tolerance and statistically significant, plus latency and cost budgets, with distinct exit codes.
It is local-first: Ollama is the default, every major hosted provider is one target: line
away (Providers), and every model call is cached by content so re-runs are free
and reproducible.
Install
pip install evalproof # or: uv add evalproof
uv tool install evalproof # just the CLI
Python 3.11 to 3.14. compare, calibrate and report work on run files and need no
model. run needs a system to evaluate: a Python function, an HTTP endpoint, a local model
(Ollama, vLLM, LM Studio, llama.cpp), or a key for a hosted provider.
What it found on a real run
A local qwen3:1.7b product support assistant, judged by qwen3:8b, 83
questions, one Apple M5. Full method and every table in MEASUREMENTS.md.
| Question | Measured |
|---|---|
| How good is the 8B judge? | TPR 92.6%, FPR 6.7%, Cohen's κ 0.78 against the answer key |
| Did swapping the grounded prompt for a "friendly" one regress quality? | −4.8 pts on the judge, 8 cases worse vs 4 better, McNemar p = 0.39 — gate warns, does not fail; a delta-only gate would have failed it |
| What did regress? | p95 latency, 1,469 → 4,422 ms; mean answer 19 → 77 tokens. A 2,500 ms budget fails the change with exit 3 |
| Does correcting the judge's rate help? | On average yes (offset 4.8 → ~3.8 pts), but with 30 labels the interval doubles; at 83 cases the judge's bias is smaller than its own noise |
| Was the gold trustworthy? | No: of 13 judge–key disagreements the key was wrong 7 times, the judge 4. Most of the "bias" corrected was the gold's |
| Is pairwise judging safer? | No: 42% of verdicts flipped with the order of the two answers, and the judge preferred the candidate 42 to 6 — mostly where both answers were right and the candidate's was five times longer |
| Does a reasoning judge help? | Against audited labels, yes: thinking on passed no wrong answer (three without it) and κ rose from 0.86–0.88 to 0.90–0.94, at 6.7× the judge time. Against the raw answer key it looked worse, because the key is wrong on exactly those cases. The gate's decision did not change |
| Is it reproducible? | 20/20 identical outputs and verdicts with the cache off; a warm-cache re-run took 0.05 s instead of 363 s; a re-judge three days later matched 83/83 |
Five-minute quickstart
The offline example lives in the repository:
git clone https://github.com/technobasant/evalproof && cd evalproof
uv sync
# Offline: no model, no network. Four versions of a ticket router.
for v in baseline regressed noisy refactored; do
uv run evalproof run examples/deterministic/suite.yaml \
--system "python:router:${v}_route" --out "runs/$v.json" --quiet
done
uv run evalproof compare runs/baseline.json runs/regressed.json \
--suite examples/deterministic/suite.yaml --gate; echo "exit $?" # 1: real regression
uv run evalproof compare runs/baseline.json runs/noisy.json \
--suite examples/deterministic/suite.yaml --gate; echo "exit $?" # 0: 2 of 60 is noise
examples/retrieval runs the same gate on a retrieval change: recall@5
does not move when the top hit drops to rank 5, while MRR and nDCG@5 do, and the gate fails
it. It was contributed by @HarshRajSinghania, and CI
checks its exit codes too.
With Ollama installed, the LLM example is
examples/support-qa (ollama pull qwen3:1.7b and
ollama pull qwen3:8b; about 6–10 minutes per run on an Apple M5).
The browser app in app/ runs locally too:
uv run --with-requirements app/requirements.txt streamlit run app/streamlit_app.py.
Providers
The target is <provider>:<model>; the model name is everything after the first colon, so
openrouter:anthropic/claude-sonnet-4.5 and ollama:qwen3:8b both work. Two native adapters
(ollama, anthropic) and one OpenAI-compatible adapter driven by a table of provider
profiles (providers/profiles.py, each row cites the
provider's documentation). Plain HTTP throughout, no vendor SDK.
| Provider | Example target | Key variable | Where |
|---|---|---|---|
ollama |
ollama:qwen3:8b |
none | local |
vllm |
vllm:meta-llama/Llama-3.1-8B-Instruct |
VLLM_API_KEY, optional |
local |
lmstudio |
lmstudio:qwen3-8b |
optional, via api_key_env |
local |
llamacpp |
llamacpp:qwen3-8b |
LLAMA_API_KEY, optional |
local |
anthropic |
anthropic:claude-sonnet-4-5 |
ANTHROPIC_API_KEY |
hosted |
openai |
openai:gpt-5 |
OPENAI_API_KEY |
hosted |
azure |
azure:<deployment> |
AZURE_OPENAI_API_KEY |
hosted, needs base_url |
gemini |
gemini:gemini-2.5-flash |
GEMINI_API_KEY |
hosted |
mistral |
mistral:mistral-large-latest |
MISTRAL_API_KEY |
hosted |
groq |
groq:llama-3.3-70b-versatile |
GROQ_API_KEY |
hosted |
together |
together:meta-llama/Llama-3.3-70B-Instruct-Turbo |
TOGETHER_API_KEY |
hosted |
fireworks |
fireworks:accounts/fireworks/models/llama-v3p3-70b-instruct |
FIREWORKS_API_KEY |
hosted |
deepseek |
deepseek:deepseek-chat |
DEEPSEEK_API_KEY |
hosted |
xai |
xai:grok-4 |
XAI_API_KEY |
hosted |
openrouter |
openrouter:anthropic/claude-sonnet-4.5 |
OPENROUTER_API_KEY |
hosted |
cerebras |
cerebras:gpt-oss-120b |
CEREBRAS_API_KEY |
hosted |
openai-compatible |
openai-compatible:<model> |
optional, via api_key_env |
any server, needs base_url |
system:
target: openai-compatible:gpt-4o # a gateway, LiteLLM proxy, TGI, SGLang, ...
base_url: https://llm-gateway.internal/v1
api_key_env: TEAM_GATEWAY_KEY # the variable to read; the key itself never goes in the suite
headers: {x-team: search} # extra HTTP headers on every call, never secrets
params: {max_tokens: 2048}
base_urloverrides any profile's default (a regional endpoint, a proxy, an olderllama-server, which listened on port 8080 before October 2026 and now defaults to 9931).api_key_envreplaces the profile's variable for any provider; a variable named there must be set.headersmerge into every request and win over the adapter's own, for exampleanthropic-version. They are not part of the cache key, and a suite file is usually committed, so keep keys in the environment.- Sampling: local servers (
ollama,vllm,lmstudio,llamacpp) receivetemperatureandseedon every call, defaults included, so a local run repeats. Hosted providers receive them only whenparamssets them, because reasoning models reject a non-default temperature; Anthropic never receives a seed, and since its current models also rejecttemperature, it gets one only when the suite asks.params.extraadds any other body field, such as{thinking: {type: adaptive}, output_config: {effort: low}}. - Thinking models spend output tokens on thinking inside
max_tokens, which defaults to 512 (changing it would change every cache key). Setparams.max_tokenshigher for them; a reply cut off before its first word, a refusal, or a content-filter block is recorded as that case's error rather than as an empty answer. - AWS Bedrock and Google Vertex AI sign requests with cloud credentials, which evalproof does
not implement. Use a gateway's OpenAI-compatible endpoint through
openai-compatible.
Concepts
Suite — one YAML file: a JSONL golden set, the system under test, scorers, an optional judge, calibration settings and a gate.
name: support-qa
dataset: cases.jsonl # {"id", "input", "reference", ...extra fields}
system:
target: ollama:qwen3:1.7b # or groq:…, anthropic:…, python:module:func, https://…
system_prompt_file: prompt.md
prompt_template: "{question}"
params: {temperature: 0, seed: 0, think: false}
judge:
target: ollama:qwen3:8b
scorers:
- {name: answer_key, type: regex, params: {any_of_field: accept, none_of_field: reject}}
- {name: judge, type: llm_judge, params: {rubric_file: rubric.md}}
calibration: {judge_scorer: judge, gold_scorer: answer_key, gold_sample: 30}
gate: {metric: judge, max_drop: 0.03, alpha: 0.05, min_cases: 40, max_p95_latency_ms: 2500}
Run — evalproof run suite.yaml writes one self-describing JSON file: every case's
output, latency, tokens and scores, plus the dataset hash, seed, Ollama version and model
digests.
Scorers — exact_match, contains, regex (accept/reject answer keys),
json_schema, numeric_tolerance, recall_at_k, mrr, ndcg, and llm_judge: a strict
JSON verdict, one retry on an unparseable reply, and an explicit undecided state that is
counted, never scored as a pass. evalproof pairwise judges two runs head to head in both
orders and reports order-dependent verdicts as ties.
Calibrate — evalproof calibrate run.json --judge-scorer judge --labels gold.jsonl
(human labels) or --gold-scorer answer_key --gold-sample 30:
| Estimate | What it is |
|---|---|
| raw judge pass rate | classify-and-count, Wilson interval |
| gold labels only | the labelled sample alone |
| ACC | (q − FPR) / (TPR − FPR), bootstrap interval over both the judged set and the gold sample |
| PPI | judge mean on unlabelled cases + mean (label − judge) on the gold sample, normal interval |
Compare and gate — evalproof compare baseline.json candidate.json --suite suite.yaml --gate
| Exit | Meaning |
|---|---|
| 0 | pass — possibly with warnings (a big drop that is not significant; a significant drop within tolerance) |
| 1 | quality regression: drop ≥ max_drop and p < alpha |
| 3 | budget breach: candidate p95 latency or cost over the limit |
| 4 | cannot gate: fewer than min_cases paired cases, or the runs used different data |
| 2 | usage or configuration error |
The gate checks one metric by default. To gate several, repeat --metric or list them in
the suite; each metric's p-value is then Holm-adjusted for the number of metrics gated, so
the chance of failing a build on noise stays at alpha for the set as a whole, and the
report shows the raw and the adjusted p-value side by side. Metrics that are not gated are
still reported.
gate:
metrics: [judge, answer_key] # one metric: `metric: judge`
max_drop: 0.03
alpha: 0.05
min_cases: 40
evalproof compare baseline.json candidate.json --gate --metric judge --metric answer_key
Import results from other tools
You do not have to run your evals with evalproof to gate them. evalproof import turns the
per-case results another tool wrote into a run file that compare and the gate read:
evalproof import promptfoo output.json --system openai:gpt-5 --out runs/candidate.json
evalproof import inspect logs/task.eval --out runs/candidate.json
evalproof import deepeval .deepeval/.latest_test_run.json --out runs/candidate.json
evalproof import lm-eval results/gpt2/samples_hellaswag_2026-11-12T10-20-30.jsonl --out runs/gpt2.json
evalproof import csv results.csv --system a --out runs/a.json # id,metric,passed,score,...
evalproof import jsonl results.jsonl --wide --id-field case --out runs/a.json # one column per metric
Import each side with the same importer, then gate as usual, for example
evalproof compare runs/baseline.json runs/candidate.json --gate --metric pass. What to know:
- Case ids are stable between runs of the same dataset (they come from the test's inputs, or the tool's own sample id, never from its position), which is what lets two files pair. The dataset hash covers the ids and inputs as the tool recorded them, so runs imported by different importers refuse to gate (exit 4) instead of pairing on a coincidence.
- A system error counts as a failure on every metric, as in a native run. Repeats of one case
(epochs, repeated tests) collapse by
--epochs:mean(the default),first,allorany. Undermean,firstandany, a case with at least one repeat that ran is not counted as a system error; its errored repeats still score as failures. - A NaN or infinite score is refused at import, naming the case and metric, because it would make the bootstrap report a significant difference that is not there.
- promptfoo files can hold several providers and
--systempicks one. Inspect.evallogs compressed with zstd need Python 3.14 or newer; otherwise runinspect log convert --to json <file>first. DeepEval's conversational cases are skipped with a warning.
From Python
The CLI is a thin layer over the same functions:
from evalproof import GateConfig, calibrate, compare_runs, decide, load_run
baseline = load_run("runs/baseline.json")
candidate = load_run("runs/candidate.json")
cmp = compare_runs(baseline, candidate) # paired cases: exact McNemar, bootstrap intervals
decision = decide(cmp, GateConfig(metric="judge", max_drop=0.03))
print(decision.status, decision.exit_code, decision.warnings)
report = calibrate(baseline, "judge", gold_scorer="answer_key", gold_sample=30)
for est in report.estimates: # raw judge rate, gold only, ACC, PPI
print(est.method, est.point, est.low, est.high)
The names in evalproof.__all__ are the supported API. Other modules are internal and may
change between minor versions; see the changelog.
Architecture
The architecture diagram is in the README on GitHub.
Decisions
| Decision | Alternative | Why | ADR |
|---|---|---|---|
| Treat the judge as a classifier to be calibrated | Trust the judge's pass rate | Its count is biased by its own error rates, and the bias moves with the true rate | 0001 |
| Local Ollama by default, HTTP-only providers, content-addressed cache | Hosted APIs and vendor SDKs | Reproducible, free to re-run, tied to a model digest; no SDK dependency | 0002 |
| Gate on "large AND significant", on paired cases | "Fail if the score dropped by X" | On a few dozen cases, X-point drops are mostly noise, and a noisy gate gets switched off | 0003 |
| One metric by default; several with Holm correction | Gate every metric at α each | Testing many metrics at α = 0.05 each inflates false failures | 0003 |
| Pointwise verdicts for gating; pairwise as a diagnostic | Pairwise preference for gating | Measured: 42% of pairwise verdicts flipped with answer order, with a strong length preference | MEASUREMENTS §6 |
| numpy and the standard library for statistics | SciPy, statsmodels | Small enough to read and to test against hand-worked values | — |
In CI
The composite action runs compare --gate, appends the report to the job summary, and
fails the job on exit codes 1, 3 or 4:
- uses: technobasant/evalproof@v0.3.0
with:
baseline: eval/baseline.json # produced on main, e.g. as a build artifact
candidate: eval/candidate.json # produced on this branch
suite: eval/suite.yaml
# metric: "judge, answer_key" # optional: gate several metrics, newline- or comma-separated
This repository's own CI runs the offline example on every commit and asserts that the gate returns 1 for the real regression and 0 for the noisy and refactored candidates.
How it relates to other tools
promptfoo (open-source, local evals of prompts, models and RAG pipelines with deterministic and model-graded assertions, a GitHub Action, and red teaming), DeepEval (pytest-style LLM tests with research-backed metrics such as G-Eval), Ragas (LLM-driven metrics and experiments for LLM and RAG applications) and Inspect (the UK AI Security Institute's framework for model and agent evaluations, with sandboxed tools and a log viewer) are broad evaluation frameworks.
evalproof is deliberately narrow: it is the measurement layer — how much a judge's verdict is worth, and whether a difference between two runs is real. Its run file is plain, documented JSON, so it can sit beside an existing harness: produce the per-case verdicts however you like, then calibrate and gate here. For promptfoo, Inspect, DeepEval and lm-eval you do not even need to do that: evalproof imports their results.
Limits
- The measurements cover one machine, two small local models, one product domain and 83 cases. They show the method; they are not a benchmark of those models.
- Calibration is only as good as its gold labels — MEASUREMENTS §4 shows a regex answer key being wrong more often than the judge. Use human labels when the decision matters.
- ACC needs both classes in the gold sample and a judge better than chance; PPI needs the gold sample to be random. evalproof reports when either does not hold rather than printing a number.
- The percentile-bootstrap p-value for continuous scores is an approximation; pass/fail metrics use the exact McNemar test.
- Cost tracking needs a price table in the suite for hosted models.
Roadmap
- Stratified gold sampling (by tag) and per-tag calibration.
Project
Changelog · Contributing · Security policy · Code of conduct · How to cite. Releases are published to PyPI from GitHub Actions with trusted publishing, and each file carries a signed provenance attestation.
Licence
Metadata
Release files for evalproof 0.3.0
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 |
|---|---|---|---|---|
| evalproof-0.3.0.tar.gz | 117.1 kB | With provenance | Details for evalproof-0.3.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| evalproof-0.3.0-py3-none-any.whl | Python 3 | none | any | Details for evalproof-0.3.0-py3-none-any.whl |
Total release size: 198.1 kB
Release files / evalproof-0.3.0.tar.gz
| Download URL | evalproof-0.3.0.tar.gz |
|---|---|
| Size | 117.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
05b9277b46ce89f382f6a3cf477899f13a4b887f7a28fca8d5717a625f79d6bb
|
|
BLAKE2b-256 checksum How to use checksums |
afd1d5949b863412cb221219406217f55f309ce13ead7af4b5c8c998f48ef3ed
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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 12, 2026.
Transparency logRelease files / evalproof-0.3.0-py3-none-any.whl
| Download URL | evalproof-0.3.0-py3-none-any.whl |
|---|---|
| Size | 81.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
a540af7c903481c2345f5115eb62f499c2652ddcfc573125cd23c1757eef7c13
|
|
BLAKE2b-256 checksum How to use checksums |
8b1096aa4d50155b1d9e262082b7cec0a627d6c12ceb9506f62550ce313d372a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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 12, 2026.
Transparency logSecurity for evalproof 0.3.0
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 evalproof-0.3.0.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 12, 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.