Encyclopedia Evalica / Evaluation / Baseline experiment
Baseline experiment
/'bay.sleyen ih'kspeh.ruh.muhnt/A specific experiment/run used as the reference point for comparisons. Baselines make regressions and improvements interpretable. (noun)
“We compared today's run against the baseline experiment from last week.”
Customer example
Dropbox moved from ad hoc spreadsheet testing to running hundreds to thousands of experiments; consistent baselines make those comparisons meaningful at that scale. Read more
Related Evaluation terms
- Absolute scoring •
- Agent •
- AI eval •
- Alignment •
- Annotation schema •
- Baseline •
- Benchmark •
- Calibration •
- CI/CD integration •
- Coherence •
- Confidence interval •
- Eval harness •
- Eval leakage •
- Experiment •
- Factuality •
- Failure mode •
- Faithfulness •
- Feedback signal •
- Groundedness •
- Hallucination •
- Inter-annotator agreement (IAA) •
- LLM-as-a-judge •
- Loop •
- Model comparison •
- Multimodal •
- Non-determinism •
- Offline evaluation •
- Pairwise evaluation •
- Pass@k •
- Playground •
- Quality gate •
- RAG (retrieval-augmented generation) •
- RAG evaluation •
- Reference-based scoring •
- Reference-free scoring •
- Regression testing •
- Release criteria •
- Remote evaluation •
- Rubric •
- Safety •
- Score distribution •
- Scorer •
- Semantic failure •
- Signal-to-noise ratio •
- Task (eval task) •
- Toxicity score
From the docs
Get started with Evals
Braintrust is the observability platform for agents in production. By actively applying intelligence to agent traces and automatically surfacing critical patterns, Braintrust helps teams at Notion, Stripe, Box, OpenAI, and Cloudflare ship quality agents at scale.
Start building