Expert dental knowledge, where models fail.

We make dental AI reliable, safe, and effective in clinical settings. Our expert network writes evals to improve AI use with gold-standard answers.

Models still fail dental case work.

Score on dentist-written case questions, by specialty. Pick a specialty to see how the top models do.

Choose a specialty
All specialties: Case score
ModelCase score
Dentist's answer88%
Claude Opus 5.532%
Gemini 4 Argon19%
GPT-6 Astra18%
General dentistry: Case score
ModelCase score
Dentist's answer97%
Gemini 4 Argon29%
Claude Opus 5.525%
GPT-6 Astra18%
Orthodontics: Case score
ModelCase score
Dentist's answer93%
Claude Opus 5.524%
Gemini 4 Argon20%
GPT-6 Astra16%
Endodontics and periodontics: Case score
ModelCase score
Dentist's answer90%
Gemini 4 Argon29%
Claude Opus 5.527%
GPT-6 Astra19%
Oral surgery: Case score
ModelCase score
Dentist's answer91%
Claude Opus 5.535%
Gemini 4 Argon27%
GPT-6 Astra20%
Pediatric dentistry: Case score
ModelCase score
Dentist's answer91%
Claude Opus 5.524%
Gemini 4 Argon21%
GPT-6 Astra16%
Medications: Case score
ModelCase score
Dentist's answer98%
Gemini 4 Argon28%
Claude Opus 5.524%
GPT-6 Astra18%

Scores are rubric-graded results earned on cases. The dentist answer is human-written, graded on the same rubric.

How we score a case

Why we built Frontier Dental

Two minutes on what we make, who writes it, and why models still get dental care wrong.

Founder, Frontier Dental · 2 min

The expert network

Every case is written by a dentist in active practice. These are the people behind the cases.

12practicing dentists

  • General dentist14 yrs · OntarioTreatment planning
  • Orthodontist9 yrs · British ColumbiaOrthodontics
  • Endodontist17 yrs · CaliforniaEndodontics
  • Pediatric dentist11 yrs · QuebecPediatric dentistry
  • Oral surgeon21 yrs · New YorkOral surgery
  • Periodontist12 yrs · AlbertaPeriodontics
  • General dentist8 yrs · TexasMedically complex patients

See the case study

Read our complete case study, including the question, rubric and every model graded answer.

Read the case study
  • 0 of 12answers passed
  • 6 of 12rubric lines no answer earned
  • 12 of 12answers missed the dentist's plan

Built for the teams that test dental AI

I work at

Dental cases for evals and post-training

  • Model-hard on your chosen cohort and pass criteria.
  • A gold-standard answer and rubric for grading.
  • Formatted to your pipeline standards.
Request a sample pack

Additional dental supply for your clients

  • Start with a pilot. 25 cases delivered in 1 month.
  • Select your specialties and clinical workflows.
  • Written and reviewed by practicing dentists.
Request a sample pack

Evaluate and fine-tune your model to sharpen your edge

  • Select the case areas where you want to improve.
  • Measure your model against a dentist's gold-standard answer.
  • Fine-tune on the gaps to build your unique edge.
Request a sample pack

Practicing dentist? Write cases with us

Start with a pilot.

Two ways to start.

Case Pilot

25 cases

Delivered in 1 month

Request a sample pack

Included

  • Model-hard on the models you name, against the pass line you set
  • Spread across the specialties you choose
  • Question, gold-standard answer, rubric and graded model answers for every case
  • Tagged by specialty and type of clinical work

Eval Pilot

50+ cases

Your dental AI, tested on dentist-written cases

Ask about an Eval Pilot

Included

  • You choose the specialty and clinical workflow
  • Your product answers a chosen set of cases
  • Every answer graded against the dentist's rubric
  • A report showing where it misses the plan a dentist would choose

How a case is made

Dentists write the cases. We keep only the ones models get wrong.

See our process

Questions buyers ask.

Who owns the cases?

Frontier Dental owns the cases it produces. Licence terms, including who else may receive a case, are agreed per project.

Is there any patient data?

No. Every case is a composite written from a dentist's experience. No names, dates or details that could identify a real patient.

Who grades the answers?

On the sample case, each answer was graded line by line by the two other models. A line counts in full when both graders agree it is met, and half when only one does.

Can we choose our own models and pass line?

Yes. You set the bar for your project.

How does a pilot work?

25 cases, delivered in 1 month, spread across specialties.

See five cases before you buy.

Five dentist-written eval cases, right in your inbox.