# How OpenEvidence uses Baseten

**23x** faster model training

As published on [baseten.co](https://www.baseten.co/resources/customers/openevidence-baseten-training/), February 2026. Captured by usedby on 2026-10-10.

- Company: [OpenEvidence](https://www.usedby.ai/companies/openevidence.md)
- Tool: [Baseten](https://www.usedby.ai/tools/baseten.md)
- Industry: [HealthTech & Digital Health](https://www.usedby.ai/companies/industry/healthtech-digital-health.md)
- Teams: machine learning

## What the story says

OpenEvidence, a medical search platform, uses Baseten Training to train its custom, domain-specific open-source models. Its machine learning team runs many training jobs in parallel on on-demand GPUs to test different hyperparameter settings and then deploys the models to production inference.

Summary written by usedby from the source page, in English. The figures are those of Baseten and OpenEvidence, not ours.

> “Baseten helped us train models to be 23x faster and is projected to save us $1.9M—while making the process so easy that even non-ML engineers could get results in under 30 minutes.”

- **30 minutes**: “even non-ML engineers could get results in under 30 minutes”

> Baseten helped us train models to be 23x faster and is projected to save us $1.9M—while making the process so easy that even non-ML engineers could get results in under 30 minutes.
>
> Eric Lehman, PhD, HEAD OF CLINICAL NLP

Source: [baseten.co](https://www.baseten.co/resources/customers/openevidence-baseten-training/), captured 2026-10-10.

> Our team spent weeks researching and vetting inference providers. It was a thorough process and we confidently believe Baseten is a clear winner.
>
> Eric Lehman, Head of Clinical NLP

Source: [baseten.co](https://www.baseten.co/resources/customers/openevidence-delivers-instant-medical-information-with-baseten/), captured 2026-10-05.

## What usedby checked

We compared the story with its live page on 2026-10-10.

- Checked: the figure 23x is on the page; its label is our wording.
- Checked: the passage quoted above is copied word for word from the page, near the name of OpenEvidence.
- Checked: the publication date is read from the page’s own metadata, never guessed.
- Checked: OpenEvidence uses Baseten. Confirmed line. Latest check across sources: 2026-10-10.
- Not checked: the result itself. We quote it; we did not measure it.

---
Source: https://www.usedby.ai/case-studies/openevidence-baseten-2 · How we check: https://www.usedby.ai/methodology