Benchmark recording · 28 September 2026

An AI agent works a MindTap-style mixed assessment

One recorded run on a benchmark replica modeled on Cengage MindTap, sped up 5×. The replica is a test copy we built, not the real site.

9 of 9graded parts correctSubmitted

Recorded 28 September 2026 · 5× speed · 3 min 51 s of real time, shown in a 53 s clip

What happens in the clip

The agent works a MindTap-style two-pane activity player: multiple choice, true/false, matching, select-all, dropdown, short-answer and fill-in-the-blank parts, one attempt per question, then submits.

Step by step

  1. Works through a MindTap-style two-pane activity player on the replica.
  2. Answers multiple choice, true/false and select-all parts.
  3. Completes matching and dropdown parts.
  4. Types short-answer and fill-in-the-blank responses.
  5. Uses one attempt per question.
  6. Submits the assessment.
  7. Replica read back: 9 of 9 graded parts correct.

What this replica tests

Two-pane activity player, custom pickers, one attempt per question. The side panel in the video shows how many graded parts are complete and whether the assignment has been turned in.

About this recording

This recording is a separate run from the scored benchmark run on 22 September 2026, and that run got the same result on this replica: 9 of 9, submitted.

A benchmark replica we built for testing, modeled on Cengage MindTap. It is not the real site, and the platform's maker is not affiliated with it and has not endorsed it. The agent is the Base plan's vision engine, run in a standalone test harness, not the full desktop app. The on-screen label “Luke’s Empire” is the benchmark’s internal name.

This clip is one of seven on the benchmark page, which has the full method and the scored results. It is also shown on the Cengage page.

Other recorded runs

Silent Student is the desktop app this engine runs in. See what it does on Cengage MindTap.

Updated 19 October 2026