All AutosheetBench tasks

Filter rows above a revenue

Spreadsheet manipulationHardDeterministic scoringLatest run

Passed by 7 of 12 products on their best model. Failed: ChatGPT in Excel, Claude Code + Sheets MCP, Claude Code + Autosheet MCP, ChatGPT + Autosheet MCP and ChatGPT in Sheets.

Prompt and starting spreadsheet

Task files

Prompt

Show rows where revenue is above 10,000.

Starting spreadsheet

Orders
ABCDEFG
1DateProductRegionSalesRevenueOrder IDAmount
22026-03-14AtlasEurope1814400O-1001720
32026-01-08BeaconNorth America118250O-1002450
42026-02-17CometEurope2718900O-1003980
52026-01-29AtlasAsia1411200O-1004610
62026-03-03BeaconEurope2216500O-1005540
72026-02-09CometNorth America97200O-1006320
82026-03-21DeltaEurope3124800O-10071250
92026-01-17DeltaAsia1612800O-1008890

A passing output

Autosheet in Excel · Opus 5.5

How each AI configuration did

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

Pass criteria

All must be met, checked automatically.
  • A filter on column E keeps values greater than 10,000

Passed 14

Autosheet in Excel Opus 5.5 · Medium

Passed9s · 3¢

Autosheet in Excel GPT-6 Astra · Low

Passed5s · 4¢

Autosheet in Sheets Opus 5.5 · Medium

Passed17s · 2¢

Autosheet in Excel Sonnet 5.5 · Medium

Passed4s · 0.9¢

Claude in Excel Opus 5.5 · High

Passed22s · 13¢

Autosheet in Excel Haiku 5.5 · High

Passed10s · 0.2¢

Claude in Sheets Opus 5.5 · Medium

Passed18s · 6¢

Autosheet in Excel GPT-6.1 Sol · Medium

Passed6s · 1¢

Autosheet in Sheets Haiku 5.5 · High

Passed24s · 0.2¢

Claude in Excel Haiku 5.5 · High

Passed10s · 0.3¢

Autosheet in Excel GPT-6 Luna · High

Passed12s · 0.2¢

Copilot in Excel Auto

Passed25s · N/A

ChatGPT + Drive MCP GPT-6 · Medium

Passed26s · N/A

Gemini in Sheets Auto

Passed34s · N/A

Failed 8

Claude Code + Sheets MCP Opus 5.5 · Medium

Failed14s · N/A

Why it failed: No filter on column E keeps values above 10,000.

Claude Code + Autosheet MCP Opus 5.5 · Medium

Failed25s · N/A

Why it failed: No filter on column E keeps values above 10,000.

ChatGPT + Autosheet MCP GPT-6 · Medium

Failed28s · N/A

Why it failed: No filter on column E keeps values above 10,000.

ChatGPT in Excel GPT-6 Astra · Medium

Failed31s · 50¢

Why it failed: Rows 3 and 7 are hidden by hand, not by a filter: the sheet has no filter to change or clear.

Claude in Sheets Haiku 5.5 · High

Failed33s · 2¢

Why it failed: No filter on column E keeps values above 10,000. Other cells of the workbook changed.

ChatGPT in Excel GPT-6 Luna · High

Failed46s · 0.7¢

Why it failed: No filter on column E keeps values above 10,000.

ChatGPT in Sheets GPT-6 Astra · Medium

Failed23s · 30¢

Why it failed: No filter on column E keeps values above 10,000.

ChatGPT in Sheets GPT-6 Luna · High

Failed22s · 0.3¢

Why it failed: No filter on column E keeps values above 10,000.