All AutosheetBench tasks

Chart sales stacked by region

ChartsMediumLLM judge scoringLatest run

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

Prompt and starting spreadsheet

Task files

Prompt

Show sales by product, stacked by region.

Starting spreadsheet

Sales
ABCD
1ProductEuropeNorth AmericaAsia
2Atlas1259884
3Beacon10211791
4Comet148132126
5Delta7689104
6Echo119108137

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.
  • A stacked chart of sales by product
  • One stacked series per region
  • Clear labels and legend; the data is unchanged

Passed 19

Autosheet in Excel Opus 5.5 · Medium

Passed9s · 3¢

Autosheet in Excel GPT-6 Astra · Low

Passed9s · 7¢

Autosheet in Sheets Opus 5.5 · Medium

Passed13s · 5¢

Autosheet in Excel Sonnet 5.5 · Medium

Passed6s · 2¢

Claude in Excel Opus 5.5 · High

Passed9s · 11¢

Autosheet in Excel Haiku 5.5 · High

Passed9s · 0.2¢

Claude in Sheets Opus 5.5 · Medium

Passed17s · 10¢

Claude Code + Sheets MCP Opus 5.5 · Medium

Passed29s · N/A

Autosheet in Excel GPT-6.1 Sol · Medium

Passed16s · 3¢

Claude Code + Autosheet MCP Opus 5.5 · Medium

Passed37s · N/A

ChatGPT + Autosheet MCP GPT-6 · Medium

Passed42s · N/A

Autosheet in Sheets Haiku 5.5 · High

Passed17s · 0.2¢

ChatGPT in Excel GPT-6 Astra · Medium

Passed22s · 39¢

Claude in Excel Haiku 5.5 · High

Passed8s · 0.4¢

Autosheet in Excel GPT-6 Luna · High

Passed17s · 0.3¢

Copilot in Excel Auto

Passed34s · N/A

ChatGPT + Drive MCP GPT-6 · Medium

Passed32s · N/A

ChatGPT in Excel GPT-6 Luna · High

Passed25s · 0.5¢

Gemini in Sheets Auto

Passed22s · N/A

Failed 3

Claude in Sheets Haiku 5.5 · High

Failed27s · 1¢

Why it failed: The legend lacks text labels (showing only colored squares), and the product category axis improperly includes 'Product' as a category label.

ChatGPT in Sheets GPT-6 Astra · Medium

Failed49s · 51¢

Why it failed: No chart object was added to the workbook.

ChatGPT in Sheets GPT-6 Luna · High

Failed29s · 0.4¢

Why it failed: No stacked chart was generated.