All AutosheetBench tasks

Highlight duplicate email addresses

FormattingEasyDeterministic scoringLatest run

Passed by 10 of 12 products on their best model. Failed: ChatGPT in Excel and ChatGPT in Sheets.

Prompt and starting spreadsheet

Task files

Prompt

Highlight duplicate email addresses.

Starting spreadsheet

Contacts
ABC
1Contact IDNameEmail
2C-101Ana Martin…@example.com
3C-102Marc Lee…@example.com
4C-103Priya Shah…@example.com
5C-104Jon Bell…@example.com
6C-105Sofia Rossi…@example.com
7C-106Nora Klein…@example.com

Expected result

How each AI configuration did

20 of 22 passRun files
Excel and Sheets · All types · All models · All outputs

Pass criteria

All must be met, checked automatically.
  • A conditional rule highlights the repeated values in C2:C7, leaving C5 and C7 as they are

Passed 20

Autosheet in Excel Opus 5.5 · Medium

Passed8s · 2¢

Autosheet in Excel GPT-6 Astra · Low

Passed5s · 4¢

Autosheet in Sheets Opus 5.5 · Medium

Passed12s · 3¢

Autosheet in Excel Sonnet 5.5 · Medium

Passed4s · 0.9¢

Claude in Excel Opus 5.5 · High

Passed24s · 14¢

Autosheet in Excel Haiku 5.5 · High

Passed8s · 0.1¢

Claude in Sheets Opus 5.5 · Medium

Passed21s · 4¢

Claude Code + Sheets MCP Opus 5.5 · Medium

Passed27s · N/A

Autosheet in Excel GPT-6.1 Sol · Medium

Passed12s · 2¢

Claude Code + Autosheet MCP Opus 5.5 · Medium

Passed31s · N/A

ChatGPT + Autosheet MCP GPT-6 · Medium

Passed43s · N/A

Autosheet in Sheets Haiku 5.5 · High

Passed18s · 0.1¢

Claude in Excel Haiku 5.5 · High

Passed14s · 0.6¢

Claude in Sheets Haiku 5.5 · High

Passed42s · 1¢

Autosheet in Excel GPT-6 Luna · High

Passed7s · 0.4¢

Copilot in Excel Auto

Passed28s · N/A

ChatGPT + Drive MCP GPT-6 · Medium

Passed28s · N/A

ChatGPT in Excel GPT-6 Luna · High

Passed24s · 0.6¢

Gemini in Sheets Auto

Passed44s · N/A

ChatGPT in Sheets GPT-6 Luna · High

Passed27s · 0.3¢

Failed 2

ChatGPT in Excel GPT-6 Astra · Medium

Failed18s · 39¢

Why it failed: The duplicate emails are filled yellow by hand: the workbook has no conditional formatting rule, so a new duplicate won't be highlighted.

ChatGPT in Sheets GPT-6 Astra · Medium

Failed19s · 31¢

Why it failed: The duplicate emails are filled yellow by hand: the sheet has no conditional formatting rule, so a new duplicate won't be highlighted.