All AutosheetBench tasks

Add in-cell bars to a column

FormattingMediumLLM judge scoringLatest run

Passed by 11 of 12 products on their best model. Failed: Gemini in Sheets.

Prompt and starting spreadsheet

Task files

Prompt

Add in-cell bars to the quantity column.

Starting spreadsheet

Inventory
ABC
1SKUProductQuantity
2SKU-101Atlas18
3SKU-102Beacon42
4SKU-103Comet7
5SKU-104Delta63
6SKU-105Echo29
7SKU-106Foxtrot51

Expected result

How each AI configuration did

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

Pass criteria

All must be met, checked by an LLM judge.
  • In-cell data bars on C2:C7
  • Bar lengths follow the quantities
  • The values stay visible and unchanged

Passed 19

Autosheet in Excel Opus 5.5 · Medium

Passed7s · 2¢

Autosheet in Excel GPT-6 Astra · Low

Passed6s · 4¢

Autosheet in Sheets Opus 5.5 · Medium

Passed14s · 10¢

Autosheet in Excel Sonnet 5.5 · Medium

Passed4s · 0.9¢

Claude in Excel Opus 5.5 · High

Passed16s · 11¢

Autosheet in Excel Haiku 5.5 · High

Passed5s · 0.1¢

Claude in Sheets Opus 5.5 · Medium

Passed35s · 6¢

Claude Code + Sheets MCP Opus 5.5 · Medium

Passed41s · N/A

Autosheet in Excel GPT-6.1 Sol · Medium

Passed13s · 1¢

Claude Code + Autosheet MCP Opus 5.5 · Medium

Passed32s · N/A

ChatGPT + Autosheet MCP GPT-6 · Medium

Passed53s · N/A

ChatGPT in Excel GPT-6 Astra · Medium

Passed33s · 42¢

Claude in Excel Haiku 5.5 · High

Passed20s · 0.7¢

Claude in Sheets Haiku 5.5 · High

Passed56s · 2¢

Autosheet in Excel GPT-6 Luna · High

Passed8s · 0.1¢

Copilot in Excel Auto

Passed19s · N/A

ChatGPT + Drive MCP GPT-6 · Medium

Passed38s · N/A

ChatGPT in Excel GPT-6 Luna · High

Passed28s · 0.6¢

ChatGPT in Sheets GPT-6 Astra · Medium

Passed41s · 47¢

Failed 3

Autosheet in Sheets Haiku 5.5 · High

Failed34s · 0.2¢

Why it failed: No in-cell data bars or SPARKLINE bars were added; only a color scale background fill was applied.

Gemini in Sheets Auto

Failed2m 29s · N/A

Why it failed: No visible bars were created in column C or as adjacent SPARKLINEs; only a solid background color gradient was applied.

ChatGPT in Sheets GPT-6 Luna · High

Failed1m 6s · 0.5¢

Why it failed: The bars are neither inside the quantity cells (Inventory!C2:C7) as conditional formatting data bars nor implemented as SPARKLINE formulas in the adjacent column; instead, REPT text…