All AutosheetBench tasks

Add a mini trend chart per product

ChartsEasyLLM judge scoringLatest run

Passed by all 12 products on their best model.

Prompt and starting spreadsheet

Task files

Prompt

Add a mini trend chart for each product.

Starting spreadsheet

Sheet1
ABCDEFG
1ProductJanFebMarAprMayJun
2Atlas120135128150162171
3Beacon908895102110118
4Comet200185190205220231
5Delta607268808896

A passing output

Autosheet in Excel · Opus 5.5

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.
  • One in-cell sparkline per product, from its row's months
  • Not one chart for the whole table
  • The data is unchanged

Passed 20

Autosheet in Excel Opus 5.5 · Medium

Passed18s · 6¢

Autosheet in Excel GPT-6 Astra · Low

Passed29s · 23¢

Autosheet in Sheets Opus 5.5 · Medium

Passed20s · 5¢

Autosheet in Excel Sonnet 5.5 · Medium

Passed11s · 2¢

Claude in Excel Opus 5.5 · High

Passed23s · 13¢

Autosheet in Excel Haiku 5.5 · High

Passed17s · 0.3¢

Claude in Sheets Opus 5.5 · Medium

Passed28s · 5¢

Claude Code + Sheets MCP Opus 5.5 · Medium

Passed41s · N/A

Claude Code + Autosheet MCP Opus 5.5 · Medium

Passed54s · N/A

ChatGPT + Autosheet MCP GPT-6 · Medium

Passed50s · N/A

Autosheet in Sheets Haiku 5.5 · High

Passed17s · 0.2¢

ChatGPT in Excel GPT-6 Astra · Medium

Passed35s · 53¢

Claude in Excel Haiku 5.5 · High

Passed15s · 0.6¢

Claude in Sheets Haiku 5.5 · High

Passed23s · 0.4¢

Autosheet in Excel GPT-6 Luna · High

Passed1m 26s · 2¢

Copilot in Excel Auto

Passed1m 19s · N/A

ChatGPT + Drive MCP GPT-6 · Medium

Passed28s · N/A

Gemini in Sheets Auto

Passed58s · N/A

ChatGPT in Sheets GPT-6 Astra · Medium

Passed41s · 54¢

ChatGPT in Sheets GPT-6 Luna · High

Passed47s · 0.6¢

Failed 2

Autosheet in Excel GPT-6.1 Sol · Medium

Failed24s · 4¢

Why it failed: No in-cell trend sparklines were added in a new column (e.g., H2:H5); no formulas or sparklines were placed in the cells.

ChatGPT in Excel GPT-6 Luna · High

Failed1m 45s · 2¢

Why it failed: No in-cell sparkline was added in a new column (column H is empty in document image output-document-001.png).