All AutosheetBench tasks

Highlight the top 10 values

FormattingMediumDeterministic scoringLatest run

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

Prompt and starting spreadsheet

Task files

Prompt

Highlight the top 10 values.

Starting spreadsheet

Sales
AB
1ProductRevenue
2Product 0112000
3Product 0219919
4Product 0327838
5Product 0435757
6Product 0543676
7Product 0651595
8Product 0759514
9Product 0867433
10Product 0975352
11Product 1083271
12Product 1191190
13Product 1212109
14Product 1320028
15Product 1427947
16Product 1535866
17Product 1643785
18Product 1751704
19Product 1859623
20Product 1967542
21Product 2075461

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 automatically.
  • A top 10 rule highlights B2:B21

Passed 19

Autosheet in Excel Opus 5.5 · Medium

Passed7s · 2¢

Autosheet in Excel GPT-6 Astra · Low

Passed10s · 14¢

Autosheet in Sheets Opus 5.5 · Medium

Passed9s · 2¢

Autosheet in Excel Sonnet 5.5 · Medium

Passed5s · 0.9¢

Claude in Excel Opus 5.5 · High

Passed19s · 11¢

Autosheet in Excel Haiku 5.5 · High

Passed8s · 0.1¢

Claude in Sheets Opus 5.5 · Medium

Passed18s · 4¢

Claude Code + Sheets MCP Opus 5.5 · Medium

Passed28s · N/A

Autosheet in Excel GPT-6.1 Sol · Medium

Passed9s · 5¢

Claude Code + Autosheet MCP Opus 5.5 · Medium

Passed38s · N/A

ChatGPT + Autosheet MCP GPT-6 · Medium

Passed52s · N/A

Autosheet in Sheets Haiku 5.5 · High

Passed16s · 0.1¢

ChatGPT in Excel GPT-6 Astra · Medium

Passed22s · 38¢

Claude in Excel Haiku 5.5 · High

Passed10s · 0.3¢

Claude in Sheets Haiku 5.5 · High

Passed20s · 1¢

Autosheet in Excel GPT-6 Luna · High

Passed19s · 0.3¢

Copilot in Excel Auto

Passed21s · N/A

ChatGPT + Drive MCP GPT-6 · Medium

Passed31s · N/A

Gemini in Sheets Auto

Passed51s · N/A

Failed 3

ChatGPT in Excel GPT-6 Luna · High

Failed22s · 0.4¢

Why it failed: No top 10 rule on B2:B21.

ChatGPT in Sheets GPT-6 Astra · Medium

Failed25s · 33¢

Why it failed: No top 10 rule on B2:B21.

ChatGPT in Sheets GPT-6 Luna · High

Failed26s · 0.3¢

Why it failed: No top 10 rule on B2:B21.