All AutosheetBench tasks

Chart enrollment, then split it by level

ChartsEasyLLM judge scoringLatest run

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

Prompt and starting spreadsheet

Task files

Prompt

Chart the overall enrollment trend over time

Split it into separate lines for undergrad and grad — I want to see them individually

Starting spreadsheet

Sheet1
ABCD
1YearUndergraduateGraduateTotal
2201814820394018760
3201915340421019550
4202015910448020390
5202116250472020970
6202216780501021790
7202317120534022460
8202417650568023330
9202518210602024230

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 by an LLM judge.
  • A trend chart of enrollment by year
  • Then undergrad and grad as separate series
  • Lines or columns, never a pie
  • The chart is updated on the second request

Passed 20

Autosheet in Excel Opus 5.5 · Medium

Passed27s · 10¢

Autosheet in Excel GPT-6 Astra · Low

Passed32s · 28¢

Autosheet in Sheets Opus 5.5 · Medium

Passed27s · 10¢

Autosheet in Excel Sonnet 5.5 · Medium

Passed13s · 4¢

Claude in Excel Opus 5.5 · High

Passed40s · 26¢

Autosheet in Excel Haiku 5.5 · High

Passed20s · 0.4¢

Claude in Sheets Opus 5.5 · Medium

Passed33s · 7¢

Claude Code + Sheets MCP Opus 5.5 · Medium

Passed40s · N/A

Autosheet in Excel GPT-6.1 Sol · Medium

Passed56s · 13¢

Claude Code + Autosheet MCP Opus 5.5 · Medium

Passed1m 15s · N/A

ChatGPT + Autosheet MCP GPT-6 · Medium

Passed1m 59s · N/A

Autosheet in Sheets Haiku 5.5 · High

Passed38s · 0.4¢

ChatGPT in Excel GPT-6 Astra · Medium

Passed46s · 88¢

Claude in Excel Haiku 5.5 · High

Passed35s · 1¢

Claude in Sheets Haiku 5.5 · High

Passed1m 15s · 3¢

Autosheet in Excel GPT-6 Luna · High

Passed1m 25s · 2¢

Copilot in Excel Auto

Passed1m 5s · N/A

ChatGPT + Drive MCP GPT-6 · Medium

Passed55s · N/A

ChatGPT in Excel GPT-6 Luna · High

Passed2m 16s · 2¢

Gemini in Sheets Auto

Passed1m 7s · N/A

Failed 2

ChatGPT in Sheets GPT-6 Astra · Medium

Failed1m 34s · $1.02

Why it failed: No native trend chart was generated in the workbook.

ChatGPT in Sheets GPT-6 Luna · High

Failed3m 1s · 2¢

Why it failed: No trend chart was created.