An AI agent works an Achieve-style statistics assignment
One recorded run on a benchmark replica modeled on Macmillan Achieve, sped up 8×. The replica is a test copy we built, not the real site.
What happens in the clip
The agent works the first third of an Achieve-style statistics assignment: box plots, numeric answers, dropdowns and a five-number summary. Partway through it stops making progress; the run ended on its idle limit and the assignment was never submitted. The clip keeps that stretch instead of cutting it.
Step by step
- Works the first third of an Achieve-style statistics assignment on the replica.
- Answers box-plot, numeric and dropdown parts.
- Works on a five-number summary.
- Stops making progress partway through; the clip keeps that stretch instead of cutting it.
- The run ends on its idle limit, and the assignment is never submitted.
- Replica read back: 6 of 8 graded parts correct.
What this replica tests
Sorting bins, numeric and short answers, image choice. 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 with a different result from the benchmark table: the scored run on 22 September 2026 got 7 of 8, not submitted; this recording got 6 of 8, not submitted.
A benchmark replica we built for testing, modeled on Macmillan Achieve. 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 Macmillan Achieve page.
Other recorded runs
- Replica modeled on WebAssign: STEM homework workbook · 8 of 8 graded parts correct, submitted
- Replica modeled on Cengage MindTap: Mixed assessment · 9 of 9 graded parts correct, submitted
- Replica modeled on McGraw Hill Connect: Accounting workbook · 106 of 109 graded parts correct, submitted
- Replica modeled on Cengage WebAssign: Calculus homework · 16 of 16 graded parts correct, submitted
- Replica modeled on Pearson MyLab Finance: Finance homework (first third) · 9 of 9 graded parts correct, submitted
- Replica modeled on Pearson MyLab College Algebra: College algebra (first third) · 5 of 5 graded parts correct, submitted
Silent Student is the desktop app this engine runs in. See what it does on Macmillan Achieve.
Updated 19 October 2026