Qwen 3.8 27B
A 27B model built by Mia to run on a single desktop-sized AI computer.
Setup and speed
Full results
- —Each task is run three times; the score counts all 1,650 attempts, not 550 tasks.
- —543 of 550 tasks were correct on all three passes — seven tasks missed, five of them on every pass.
- —The misses are consistent, not random: one spreadsheet analysis named the wrong supplier, two ran out of tool steps, three SQL queries returned the wrong rows, and one business reply cited the wrong reference number.
- —Nothing was cut off by the output limit — every miss was a wrong answer, not a truncated one.
The first token arrives at 0.38s and the answer starts straight away — this model does not run a separate reasoning phase. The 23.2s typical task time is the answer being written.
Files it produced
Four real documents from one fact sheet, produced once. Passed is machine-checked against the fact sheet and the brief; quality is a separate 1–5 score from a published rubric and never changes whether a file passed. How files are graded →
An 8–12 page annual report with six required sections: shareholder letter, financial review, category performance, customer and geographic performance, risk factors, and outlook.
Download DOCXA two-sheet workbook: a Summary comparing FY2025 to FY2024, and a Monthly sheet with all twelve months.
Download XLSXA ten-slide investor presentation following a fixed outline, with the brand palette applied and at least one real chart object.
Download PPTXAn X post of 280 characters or fewer and a LinkedIn post, both announcing the results, text only.
Download MDEvery artifact below is the file the model actually produced, published unedited so you can open it yourself. These are AI-generated documents about a fictional company — read them as samples of the model's work, not as advice or a real annual report. The workbook's formula cells hold real formulas — a viewer that does not recalculate may show them blank until Excel opens the file.