AI Compare · Test kit
Analyze a spreadsheet and get the numbers right
Forty orders with cancelled and refunded rows, two missing prices and a correction row with negative units. The answers are fixed, so you can check them exactly.
Prices for United States, before sales tax Data release 2026.10.16-3, Oct 16, 2026 Rules 2.1.0
Run the test
- Download the file for the AI.
- Copy the prompt.
Using the attached CSV only: (1) total revenue from shipped orders, where revenue = units x unit_price_usd x (1 - discount_pct/100), leaving out rows without a price; (2) the region with the highest shipped revenue and its revenue; (3) how many rows have no unit price; (4) the average discount_pct across all shipped orders. Show how you calculated each answer and list every row you left out and why.
- Open the AI in another tab, in your own account, start a fresh chat, attach the file and paste the prompt.
- Note what you used: the plan, the visible model or mode, whether web search was on, how many attempts it took and anything that went wrong.
- Score the answer with the checks below. Run the same kit in each AI you are choosing between, or paste their answers into the blind review.
Scorecard
Critical checks are marked. One failed critical check matters more than a nice style.
- Total shipped revenue (USD)Critical
- Top region by shipped revenueCritical
- Rows with no unit priceCritical
- Average discount on shipped orders (%)
- Lists the rows it left out and whyCritical
- Treats the negative-units row (HL-1022) as a correction, not an error to drop silently
Compare answers blind
Paste the answer each AI gave, score them without seeing which AI wrote which, then reveal. You ran the tests yourself, so you may still recognise a style: hiding the names reduces that bias, it does not remove it. The answers stay in this tab and are never saved or sent anywhere; only the scores are kept, on this device, when you reveal.
Reference answer (open after you score)
Revenue 7548.63 USD (exactly 7548.625; answers within one cent are accepted) from 35 shipped orders (two shipped rows have no price and are left out). Top region East with 2329.08 USD. 2 rows have no unit price. Average discount on shipped orders 5.00%. HL-1022 has -2 units: a correction that lowers revenue; it should be included or at least flagged, never silently dropped.
Kit version 1.0.0, files frozen on Oct 12, 2026. Original fixture by What the tech, released under CC BY 4.0. Fictional people, companies and figures. A passing score shows how one answer did on this kit; it does not prove the tool is generally better.