Skip to main content
← Back to iBacalao

Model transparency

How iBacalao's review AI works

iBacalao uses AI with subject-, criterion-, level- and session-specific context to review coursework drafts. This page describes the review workflow, internal QA, and the limits of what an iBacalao score means.

Last transparency review: 3 October 2026. Publishing and correction standards are described in our editorial policy.

How review context is applied

The review workflow applies configured rubric, subject, level and assessment-session context to a provided draft.

Context helps frame the feedback. It does not establish that a score is correct or that it matches an IB examiner's judgment.

What has been evaluated

Internal QA has tested whether feedback is specific, uses appropriate IB vocabulary, respects student level, scales with draft sophistication, and gives actionable next steps. We also compare language paths and inspect criterion-selection errors and factual mistakes.

Some internal QA uses another language model as a judge. That is an engineering test, not an independent examiner study. It can reveal regressions and inconsistencies, but it does not establish agreement with IB examiners or predict a final moderated grade.

What we do not claim

  • We do not claim that an iBacalao score is an official International Baccalaureate grade or predicted final grade.
  • We do not claim examiner-equivalent scoring accuracy.
  • We do not currently publish a blinded human-examiner benchmark with agreement, error or calibration statistics.

Independence Notice

iBacalao is an independent product and is not affiliated with, endorsed by, sponsored by or approved by the International Baccalaureate Organization.