Benchmarking Excel and Sheets AI

AutosheetBench evaluates real AI products on realistic spreadsheet tasks.

Latest run Code on GitHubDataset on Hugging Face

At a glance

Score on 187 tasks

Higher is better
97.3%
Autosheet in Excel
91.4%
Claude in Excel
86.1%
ChatGPT in Excel
81.8%
Copilot in Excel
74.9%
Gemini in Sheets

Time per task

Lower is better
27s
Autosheet in Excel
44s
Copilot in Excel
55s
Claude in Excel
59s
ChatGPT in Excel
2m 6s
Gemini in Sheets

AI cost per task

Lower is better
12¢
Autosheet in Excel
13¢
Gemini in Sheets
17¢
Copilot in Excel
35¢
Claude in Excel
76¢
ChatGPT in Excel

Sidebar add-ons, each on its best model and platform.

What is AI cost and how is it computed?
AutosheetBench at a glance: each product's score on the 187 tasks, its average time per task and its average AI cost per task. Sidebar add-ons, each on its best model and platform. Latest run November 17, 2026.
ProductModelEffortScore on 187 tasksTime per taskAI cost per taskAI cost kind
Autosheet in ExcelOpus 5.5Medium97.3%27s12¢Tokens at API list prices
Claude in ExcelOpus 5.5High91.4%55s35¢Tokens at API list prices
ChatGPT in ExcelGPT-6 AstraMedium86.1%59s76¢Tokens at API list prices
Copilot in ExcelAutoAuto81.8%44s17¢Plan's month (no tokens recorded)
Gemini in SheetsAutoAuto74.9%2m 6s13¢Plan's month (no tokens recorded)

Explore score, duration, cost in detail

Every add-on and MCP on each model it ran, with filters for platform, product type and model.

Excel and Sheets · All types · Best models

Overall score

Excel
Sidebar add-ons
  1. 97.3%
    Autosheetin ExcelOpus 5.5
  2. 91.4%
    Claudein ExcelOpus 5.5
  3. 86.1%
    ChatGPTin ExcelGPT-6 Astra
  4. 81.8%
    Copilotin ExcelAuto
Google Sheets
Sidebar add-ons
  1. 92.0%
    Autosheetin SheetsOpus 5.5
  2. 89.8%
    Claudein SheetsOpus 5.5
  3. 74.9%
    Geminiin SheetsAuto
  4. 62.0%
    ChatGPTin SheetsGPT-6 Astra
AI assistant + MCP
  1. 89.8%
    Claude Code+ Sheets
    MCP
    Opus 5.5
  2. 88.8%
    Claude Code+ Autosheet
    MCP
    Opus 5.5
  3. 87.2%
    ChatGPT+ Autosheet
    MCP
    GPT-6
  4. 81.8%
    ChatGPT+ Drive
    MCP
    GPT-6
AutosheetBench overall scores: share of the 187 tasks each configuration passed. Every configuration, in Excel and Google Sheets. Latest run November 17, 2026.
ProductPlatformTypeModelMCP modelEffortOverall score (%)Tasks scored
Autosheet in ExcelExcelSidebar add-onOpus 5.5Medium97.3187
Autosheet in ExcelExcelSidebar add-onGPT-6 AstraLow92.5187
Autosheet in ExcelExcelSidebar add-onSonnet 5.5Medium92.0187
Autosheet in ExcelExcelSidebar add-onHaiku 5.5High91.4187
Claude in ExcelExcelSidebar add-onOpus 5.5High91.4187
Autosheet in ExcelExcelSidebar add-onGPT-6.1 SolMedium89.8187
ChatGPT in ExcelExcelSidebar add-onGPT-6 AstraMedium86.1187
Claude in ExcelExcelSidebar add-onHaiku 5.5High84.5187
Autosheet in ExcelExcelSidebar add-onGPT-6 LunaHigh83.4187
Copilot in ExcelExcelSidebar add-onAutoAuto81.8187
ChatGPT in ExcelExcelSidebar add-onGPT-6 LunaHigh76.5187
Autosheet in SheetsGoogle SheetsSidebar add-onOpus 5.5Medium92.0187
Claude in SheetsGoogle SheetsSidebar add-onOpus 5.5Medium89.8187
Autosheet in SheetsGoogle SheetsSidebar add-onHaiku 5.5High87.2187
Claude in SheetsGoogle SheetsSidebar add-onHaiku 5.5High84.5187
Gemini in SheetsGoogle SheetsSidebar add-onAutoAuto74.9187
ChatGPT in SheetsGoogle SheetsSidebar add-onGPT-6 AstraMedium62.0187
ChatGPT in SheetsGoogle SheetsSidebar add-onGPT-6 LunaHigh57.2187
Claude Code + Sheets MCPGoogle SheetsAI assistant + MCPOpus 5.5Medium89.8187
Claude Code + Autosheet MCPGoogle SheetsAI assistant + MCPOpus 5.5Opus 5.5Medium88.8187
ChatGPT + Autosheet MCPGoogle SheetsAI assistant + MCPGPT-6Opus 5.5Medium87.2187
ChatGPT + Drive MCPGoogle SheetsAI assistant + MCPGPT-6Medium81.8187

Score vs duration

Autosheet in ExcelClaude in ExcelChatGPT in ExcelCopilot in ExcelAutosheet in SheetsClaude in SheetsGemini in SheetsChatGPT in SheetsClaude Code + Sheets MCPClaude Code + Autosheet MCPChatGPT + Autosheet MCPChatGPT + Drive MCP
Overall score →60%70%80%90%100%0s30s1m1m 30s2m2m 30sAverage duration per task →Most attractive quadrant+GPT-6+GPT-6+Opus 5.5+Opus 5.5GPT-6 AstraAutoAutoGPT-6 AstraOpus 5.5Opus 5.5Opus 5.5Opus 5.5
AutosheetBench scores and durations: share of the 187 tasks each configuration passed, and its average duration per task. Every configuration, in Excel and Google Sheets. Latest run November 17, 2026.
ProductPlatformTypeModelMCP modelEffortOverall score (%)Average duration per task (s)
Autosheet in ExcelExcelSidebar add-onOpus 5.5Medium97.327
Autosheet in ExcelExcelSidebar add-onGPT-6 AstraLow92.529
Autosheet in ExcelExcelSidebar add-onSonnet 5.5Medium92.016
Autosheet in ExcelExcelSidebar add-onHaiku 5.5High91.428
Claude in ExcelExcelSidebar add-onOpus 5.5High91.455
Autosheet in ExcelExcelSidebar add-onGPT-6.1 SolMedium89.832
ChatGPT in ExcelExcelSidebar add-onGPT-6 AstraMedium86.159
Claude in ExcelExcelSidebar add-onHaiku 5.5High84.541
Autosheet in ExcelExcelSidebar add-onGPT-6 LunaHigh83.433
Copilot in ExcelExcelSidebar add-onAutoAuto81.844
ChatGPT in ExcelExcelSidebar add-onGPT-6 LunaHigh76.567
Autosheet in SheetsGoogle SheetsSidebar add-onOpus 5.5Medium92.039
Claude in SheetsGoogle SheetsSidebar add-onOpus 5.5Medium89.861
Autosheet in SheetsGoogle SheetsSidebar add-onHaiku 5.5High87.250
Claude in SheetsGoogle SheetsSidebar add-onHaiku 5.5High84.570
Gemini in SheetsGoogle SheetsSidebar add-onAutoAuto74.9126
ChatGPT in SheetsGoogle SheetsSidebar add-onGPT-6 AstraMedium62.066
ChatGPT in SheetsGoogle SheetsSidebar add-onGPT-6 LunaHigh57.272
Claude Code + Sheets MCPGoogle SheetsAI assistant + MCPOpus 5.5Medium89.873
Claude Code + Autosheet MCPGoogle SheetsAI assistant + MCPOpus 5.5Opus 5.5Medium88.875
ChatGPT + Autosheet MCPGoogle SheetsAI assistant + MCPGPT-6Opus 5.5Medium87.275
ChatGPT + Drive MCPGoogle SheetsAI assistant + MCPGPT-6Medium81.846
Autosheet in ExcelClaude in ExcelChatGPT in ExcelCopilot in ExcelAutosheet in SheetsClaude in SheetsGemini in SheetsChatGPT in Sheets
Overall score →60%70%80%90%100%0¢25¢50¢75¢$1.00$1.25AI cost per task →Most attractive quadrantChatGPT in Sheets · GPT-6 Astra: 62.0%, 80¢GPT-6 AstraGemini in Sheets · Auto: 74.9%, 13¢, the plan's month: no tokens recordedAutoCopilot in Excel · Auto: 81.8%, 17¢, the plan's month: no tokens recordedAutoChatGPT in Excel · GPT-6 Astra: 86.1%, 76¢GPT-6 AstraClaude in Sheets · Opus 5.5: 89.8%, 24¢Opus 5.5Claude in Excel · Opus 5.5: 91.4%, 35¢Opus 5.5Autosheet in Sheets · Opus 5.5: 92.0%, 14¢Opus 5.5Autosheet in Excel · Opus 5.5: 97.3%, 12¢Opus 5.5
AutosheetBench scores and AI costs: share of the 187 tasks each configuration passed, and the AI cost of one run of every task. Every configuration, in Excel and Google Sheets. Latest run November 17, 2026.
ProductPlatformTypeModelMCP modelEffortOverall score (%)AI cost of one run of every task ($)AI cost kind
Autosheet in ExcelExcelSidebar add-onOpus 5.5Medium97.322.30Tokens at API list prices
Autosheet in ExcelExcelSidebar add-onGPT-6 AstraLow92.533.81Tokens at API list prices
Autosheet in ExcelExcelSidebar add-onSonnet 5.5Medium92.012.39Tokens at API list prices
Autosheet in ExcelExcelSidebar add-onHaiku 5.5High91.410.35Tokens at API list prices
Claude in ExcelExcelSidebar add-onOpus 5.5High91.465.73Tokens at API list prices
Autosheet in ExcelExcelSidebar add-onGPT-6.1 SolMedium89.819.52Tokens at API list prices
ChatGPT in ExcelExcelSidebar add-onGPT-6 AstraMedium86.1141.97Tokens at API list prices
Claude in ExcelExcelSidebar add-onHaiku 5.5High84.57.14Tokens at API list prices
Autosheet in ExcelExcelSidebar add-onGPT-6 LunaHigh83.411.59Tokens at API list prices
Copilot in ExcelExcelSidebar add-onAutoAuto81.831.50Plan's month (no tokens recorded)
ChatGPT in ExcelExcelSidebar add-onGPT-6 LunaHigh76.52.16Tokens at API list prices
Autosheet in SheetsGoogle SheetsSidebar add-onOpus 5.5Medium92.025.83Tokens at API list prices
Claude in SheetsGoogle SheetsSidebar add-onOpus 5.5Medium89.845.18Tokens at API list prices
Autosheet in SheetsGoogle SheetsSidebar add-onHaiku 5.5High87.212.37Tokens at API list prices
Claude in SheetsGoogle SheetsSidebar add-onHaiku 5.5High84.59.34Tokens at API list prices
Gemini in SheetsGoogle SheetsSidebar add-onAutoAuto74.924.00Plan's month (no tokens recorded)
ChatGPT in SheetsGoogle SheetsSidebar add-onGPT-6 AstraMedium62.0149.88Tokens at API list prices
ChatGPT in SheetsGoogle SheetsSidebar add-onGPT-6 LunaHigh57.21.47Tokens at API list prices
Claude Code + Sheets MCPGoogle SheetsAI assistant + MCPOpus 5.5Medium89.8No dataNo data
Claude Code + Autosheet MCPGoogle SheetsAI assistant + MCPOpus 5.5Opus 5.5Medium88.8No dataNo data
ChatGPT + Autosheet MCPGoogle SheetsAI assistant + MCPGPT-6Opus 5.5Medium87.2No dataNo data
ChatGPT + Drive MCPGoogle SheetsAI assistant + MCPGPT-6Medium81.8No dataNo data

Score by capability

255075100FormulasSpreadsheetmanipulationChartsData operationsFormattingPivot tablesBulk contentgenerationBulk dataprocessingAutosheet in Excel, Opus 5.5: Formulas 100.0%Autosheet in Excel, Opus 5.5: Spreadsheet manipulation 100.0%Autosheet in Excel, Opus 5.5: Charts 96.7%Autosheet in Excel, Opus 5.5: Data operations 100.0%Autosheet in Excel, Opus 5.5: Formatting 96.2%Autosheet in Excel, Opus 5.5: Pivot tables 87.5%Autosheet in Excel, Opus 5.5: Bulk content generation 100.0%Autosheet in Excel, Opus 5.5: Bulk data processing 88.2%Claude in Excel, Opus 5.5: Formulas 100.0%Claude in Excel, Opus 5.5: Spreadsheet manipulation 100.0%Claude in Excel, Opus 5.5: Charts 93.3%Claude in Excel, Opus 5.5: Data operations 100.0%Claude in Excel, Opus 5.5: Formatting 88.5%Claude in Excel, Opus 5.5: Pivot tables 87.5%Claude in Excel, Opus 5.5: Bulk content generation 36.4%Claude in Excel, Opus 5.5: Bulk data processing 82.4%ChatGPT in Excel, GPT-6 Astra: Formulas 100.0%ChatGPT in Excel, GPT-6 Astra: Spreadsheet manipulation 94.4%ChatGPT in Excel, GPT-6 Astra: Charts 80.0%ChatGPT in Excel, GPT-6 Astra: Data operations 94.1%ChatGPT in Excel, GPT-6 Astra: Formatting 76.9%ChatGPT in Excel, GPT-6 Astra: Pivot tables 87.5%ChatGPT in Excel, GPT-6 Astra: Bulk content generation 36.4%ChatGPT in Excel, GPT-6 Astra: Bulk data processing 82.4%Copilot in Excel, Auto: Formulas 100.0%Copilot in Excel, Auto: Spreadsheet manipulation 91.7%Copilot in Excel, Auto: Charts 70.0%Copilot in Excel, Auto: Data operations 88.2%Copilot in Excel, Auto: Formatting 80.8%Copilot in Excel, Auto: Pivot tables 100.0%Copilot in Excel, Auto: Bulk content generation 18.2%Copilot in Excel, Auto: Bulk data processing 64.7%Autosheet in Sheets, Opus 5.5: Formulas 97.6%Autosheet in Sheets, Opus 5.5: Spreadsheet manipulation 97.2%Autosheet in Sheets, Opus 5.5: Charts 83.3%Autosheet in Sheets, Opus 5.5: Data operations 94.1%Autosheet in Sheets, Opus 5.5: Formatting 92.3%Autosheet in Sheets, Opus 5.5: Pivot tables 87.5%Autosheet in Sheets, Opus 5.5: Bulk content generation 81.8%Autosheet in Sheets, Opus 5.5: Bulk data processing 88.2%Claude in Sheets, Opus 5.5: Formulas 100.0%Claude in Sheets, Opus 5.5: Spreadsheet manipulation 94.4%Claude in Sheets, Opus 5.5: Charts 86.7%Claude in Sheets, Opus 5.5: Data operations 100.0%Claude in Sheets, Opus 5.5: Formatting 88.5%Claude in Sheets, Opus 5.5: Pivot tables 87.5%Claude in Sheets, Opus 5.5: Bulk content generation 36.4%Claude in Sheets, Opus 5.5: Bulk data processing 88.2%Gemini in Sheets, Auto: Formulas 83.3%Gemini in Sheets, Auto: Spreadsheet manipulation 86.1%Gemini in Sheets, Auto: Charts 60.0%Gemini in Sheets, Auto: Data operations 88.2%Gemini in Sheets, Auto: Formatting 80.8%Gemini in Sheets, Auto: Pivot tables 87.5%Gemini in Sheets, Auto: Bulk content generation 9.1%Gemini in Sheets, Auto: Bulk data processing 70.6%ChatGPT in Sheets, GPT-6 Astra: Formulas 97.6%ChatGPT in Sheets, GPT-6 Astra: Spreadsheet manipulation 80.6%ChatGPT in Sheets, GPT-6 Astra: Charts 3.3%ChatGPT in Sheets, GPT-6 Astra: Data operations 82.4%ChatGPT in Sheets, GPT-6 Astra: Formatting 50.0%ChatGPT in Sheets, GPT-6 Astra: Pivot tables 0.0%ChatGPT in Sheets, GPT-6 Astra: Bulk content generation 27.3%ChatGPT in Sheets, GPT-6 Astra: Bulk data processing 88.2%Claude Code + Sheets MCP, Opus 5.5: Formulas 100.0%Claude Code + Sheets MCP, Opus 5.5: Spreadsheet manipulation 97.2%Claude Code + Sheets MCP, Opus 5.5: Charts 73.3%Claude Code + Sheets MCP, Opus 5.5: Data operations 100.0%Claude Code + Sheets MCP, Opus 5.5: Formatting 88.5%Claude Code + Sheets MCP, Opus 5.5: Pivot tables 87.5%Claude Code + Sheets MCP, Opus 5.5: Bulk content generation 54.5%Claude Code + Sheets MCP, Opus 5.5: Bulk data processing 94.1%Claude Code + Autosheet MCP, Opus 5.5: Formulas 95.2%Claude Code + Autosheet MCP, Opus 5.5: Spreadsheet manipulation 97.2%Claude Code + Autosheet MCP, Opus 5.5: Charts 66.7%Claude Code + Autosheet MCP, Opus 5.5: Data operations 100.0%Claude Code + Autosheet MCP, Opus 5.5: Formatting 88.5%Claude Code + Autosheet MCP, Opus 5.5: Pivot tables 100.0%Claude Code + Autosheet MCP, Opus 5.5: Bulk content generation 90.9%Claude Code + Autosheet MCP, Opus 5.5: Bulk data processing 76.5%ChatGPT + Autosheet MCP, GPT-6: Formulas 92.9%ChatGPT + Autosheet MCP, GPT-6: Spreadsheet manipulation 91.7%ChatGPT + Autosheet MCP, GPT-6: Charts 76.7%ChatGPT + Autosheet MCP, GPT-6: Data operations 94.1%ChatGPT + Autosheet MCP, GPT-6: Formatting 84.6%ChatGPT + Autosheet MCP, GPT-6: Pivot tables 87.5%ChatGPT + Autosheet MCP, GPT-6: Bulk content generation 81.8%ChatGPT + Autosheet MCP, GPT-6: Bulk data processing 82.4%ChatGPT + Drive MCP, GPT-6: Formulas 100.0%ChatGPT + Drive MCP, GPT-6: Spreadsheet manipulation 97.2%ChatGPT + Drive MCP, GPT-6: Charts 60.0%ChatGPT + Drive MCP, GPT-6: Data operations 94.1%ChatGPT + Drive MCP, GPT-6: Formatting 88.5%ChatGPT + Drive MCP, GPT-6: Pivot tables 87.5%ChatGPT + Drive MCP, GPT-6: Bulk content generation 18.2%ChatGPT + Drive MCP, GPT-6: Bulk data processing 58.8%
Overall and capability scores of the configurations shown, a row each, the capabilities in the radar's order. Select a configuration to keep its shape forward.
OverallFormulasSpreadsheet manipulationChartsData operationsFormattingPivot tablesBulk content generationBulk data processing
Excel · Sidebar add-ons
97.3100.0100.096.7100.096.287.5100.088.2
91.4100.0100.093.3100.088.587.536.482.4
86.1100.094.480.094.176.987.536.482.4
81.8100.091.770.088.280.8100.018.264.7
Google Sheets · Sidebar add-ons
92.097.697.283.394.192.387.581.888.2
89.8100.094.486.7100.088.587.536.488.2
74.983.386.160.088.280.887.59.170.6
62.097.680.63.382.450.00.027.388.2
Google Sheets · AI assistant + MCP
89.8100.097.273.3100.088.587.554.594.1
88.895.297.266.7100.088.5100.090.976.5
87.292.991.776.794.184.687.581.882.4
81.8100.097.260.094.188.587.518.258.8

Below 90%Above 90%

AutosheetBench scores by capability: share of the 187 tasks each configuration passed, its average duration per task, and its score in each of the 8 capabilities. Every configuration, in Excel and Google Sheets. Latest run November 17, 2026.
ProductPlatformTypeModelMCP modelEffortOverall score (%)Average duration per task (s)Formulas (%)Spreadsheet manipulation (%)Charts (%)Data operations (%)Formatting (%)Pivot tables (%)Bulk content generation (%)Bulk data processing (%)
Autosheet in ExcelExcelSidebar add-onOpus 5.5Medium97.327100.0100.096.7100.096.287.5100.088.2
Autosheet in ExcelExcelSidebar add-onGPT-6 AstraLow92.52997.694.490.088.292.387.581.894.1
Autosheet in ExcelExcelSidebar add-onSonnet 5.5Medium92.016100.094.493.394.188.587.563.688.2
Autosheet in ExcelExcelSidebar add-onHaiku 5.5High91.428100.097.296.782.484.6100.063.682.4
Claude in ExcelExcelSidebar add-onOpus 5.5High91.455100.0100.093.3100.088.587.536.482.4
Autosheet in ExcelExcelSidebar add-onGPT-6.1 SolMedium89.832100.094.480.094.184.687.563.694.1
ChatGPT in ExcelExcelSidebar add-onGPT-6 AstraMedium86.159100.094.480.094.176.987.536.482.4
Claude in ExcelExcelSidebar add-onHaiku 5.5High84.54192.994.486.788.284.687.527.370.6
Autosheet in ExcelExcelSidebar add-onGPT-6 LunaHigh83.433100.086.176.782.476.987.545.582.4
Copilot in ExcelExcelSidebar add-onAutoAuto81.844100.091.770.088.280.8100.018.264.7
ChatGPT in ExcelExcelSidebar add-onGPT-6 LunaHigh76.567100.086.156.794.176.962.50.070.6
Autosheet in SheetsGoogle SheetsSidebar add-onOpus 5.5Medium92.03997.697.283.394.192.387.581.888.2
Claude in SheetsGoogle SheetsSidebar add-onOpus 5.5Medium89.861100.094.486.7100.088.587.536.488.2
Autosheet in SheetsGoogle SheetsSidebar add-onHaiku 5.5High87.250100.094.470.082.488.587.581.876.5
Claude in SheetsGoogle SheetsSidebar add-onHaiku 5.5High84.570100.088.973.388.288.575.045.576.5
Gemini in SheetsGoogle SheetsSidebar add-onAutoAuto74.912683.386.160.088.280.887.59.170.6
ChatGPT in SheetsGoogle SheetsSidebar add-onGPT-6 AstraMedium62.06697.680.63.382.450.00.027.388.2
ChatGPT in SheetsGoogle SheetsSidebar add-onGPT-6 LunaHigh57.27297.683.33.370.646.20.00.064.7
Claude Code + Sheets MCPGoogle SheetsAI assistant + MCPOpus 5.5Medium89.873100.097.273.3100.088.587.554.594.1
Claude Code + Autosheet MCPGoogle SheetsAI assistant + MCPOpus 5.5Opus 5.5Medium88.87595.297.266.7100.088.5100.090.976.5
ChatGPT + Autosheet MCPGoogle SheetsAI assistant + MCPGPT-6Opus 5.5Medium87.27592.991.776.794.184.687.581.882.4
ChatGPT + Drive MCPGoogle SheetsAI assistant + MCPGPT-6Medium81.846100.097.260.094.188.587.518.258.8

Score by task

  • Passed
  • Failed
  • Autosheet in Excel
  • Autosheet in Sheets
  • Claude in Excel
  • Claude Code + Sheets MCP
  • Claude in Sheets
  • Claude Code + Autosheet MCP
  • ChatGPT + Autosheet MCP
  • ChatGPT in Excel
  • ChatGPT + Drive MCP
  • Copilot in Excel
  • Gemini in Sheets
  • ChatGPT in Sheets
Formulas
Spreadsheet manipulation
Charts
Data operations
Formatting
Pivot tables
Bulk content generation
Bulk data processing
AutosheetBench score by task: how many of the 187 tasks each configuration passed and failed, and the titles of the tasks it failed. Every configuration, in Excel and Google Sheets. Latest run November 17, 2026. Each task's result for every configuration is in https://autosheet.com/benchmark/task-results.csv.
ProductPlatformTypeModelMCP modelEffortOverall score (%)Tasks passedTasks failedTitles of the tasks failed
Autosheet in ExcelExcelSidebar add-onOpus 5.5Medium97.31825Make a pie chart of revenue by year; Add thousands separators; Pivot revenue, cost and margin; Categorize support tickets; Normalize ticket priorities
Autosheet in ExcelExcelSidebar add-onGPT-6 AstraLow92.517314Build a cover sheet for a project plan; Align zero on a dual-axis combo chart; Show a chart's labels as whole percentages; Make a pie chart of revenue by year; Add seniority columns in the table's format; Format amounts as US dollars; Pivot revenue, cost and margin; Normalize ticket priorities; Generate 1,000 sample CRM records; Sort by date, oldest first; Fix broken formulas and validate amounts; Look up and color letter grades; Fix numbers stored as text; Translate HTML descriptions
Autosheet in ExcelExcelSidebar add-onSonnet 5.5Medium92.017215Add a cover page to an annual report; Show a chart's labels as whole percentages; Make a pie chart of revenue by year; Add a matching table of failed tool calls; Add thousands separators; Make a table look professional; Pivot revenue, cost and margin; Normalize ticket priorities; Find and replace a year in text; Generate 1,000 sample CRM records; Group rows by category; Summarize support tickets; Tag the main theme of each review; Translate a catalog into English; Translate tickets into English
Autosheet in ExcelExcelSidebar add-onHaiku 5.5High91.417116Show a chart's labels as whole percentages; Add seniority columns in the table's format; Format amounts as US dollars; Add thousands separators; Make a table look professional; Classify the sentiment of tickets; Normalize ticket priorities; Add checkboxes to a range; Generate 1,000 sample CRM records; Group rows by category; Rewrite product descriptions in place; Rate the quality of product listings; Fix broken formulas and validate amounts; Fix numbers stored as text; Translate HTML descriptions; Translate tickets into English
Claude in ExcelExcelSidebar add-onOpus 5.5High91.417116Combine revenue bars with a rate line; Make a pie chart of revenue by year; Format amounts as US dollars; Add thousands separators; Make a table look professional; Pivot revenue, cost and margin; Categorize support tickets; Classify the sentiment of tickets; Draft a reply to each review; Find each company's headquarters; Generate 1,000 sample CRM records; Rewrite product descriptions in place; Summarize support tickets; Translate HTML descriptions; Translate reviews into English; Translate tickets into English
Autosheet in ExcelExcelSidebar add-onGPT-6.1 SolMedium89.816819Add a mini trend chart per product; Align zero on a dual-axis combo chart; Show a chart's labels as whole percentages; Make a pie chart of revenue by year; Split two series onto their own axes; Build an e-commerce KPI dashboard; Add seniority columns in the table's format; Add a matching table of failed tool calls; Format amounts as US dollars; Add thousands separators; Pivot revenue, cost and margin; Normalize ticket priorities; Freeze the top row and three columns; Generate 1,000 sample CRM records; Sort by date, oldest first; Summarize job descriptions; Summarize reviews in one line; Summarize support tickets; Fix broken formulas and validate amounts
ChatGPT in ExcelExcelSidebar add-onGPT-6 AstraMedium86.116126Combine revenue bars with a rate line; Create a Gantt chart; Show a chart's labels as whole percentages; Make a pie chart of revenue by year; Split two series onto their own axes; Chart traffic sources, then make it a pie; Add seniority columns in the table's format; Highlight duplicate email addresses; Highlight revenues above a threshold; Format amounts as US dollars; Add thousands separators; Make a table look professional; Pivot revenue, cost and margin; Categorize support tickets; Classify the sentiment of tickets; Filter rows above a revenue; Filter to one region; Find each company's headquarters; Write SEO descriptions; Generate 1,000 sample CRM records; Rewrite product descriptions in place; Summarize reviews in one line; Summarize support tickets; Fix broken formulas and validate amounts; Translate HTML descriptions; Translate tickets into English
Claude in ExcelExcelSidebar add-onHaiku 5.5High84.515829Combine revenue bars with a rate line; Use a log scale on data with zeros; Make a pie chart of revenue by year; Chart the top 10 products plus Other; Add a matching table of failed tool calls; Format amounts as US dollars; Add thousands separators; Make a table look professional; Combine first and last names; Count the days since each inquiry; Split full names into first and last; Pivot revenue, cost and margin; Categorize support tickets; Classify the sentiment of tickets; Add checkboxes to a range; Detect salary ranges in job posts; Draft a reply to each review; Generate 1,000 sample CRM records; Group rows by category; Rewrite product descriptions in place; Rate the quality of product listings; Sort a table with merged cells; Summarize job descriptions; Summarize support tickets; Fix broken formulas and validate amounts; Tag the main theme of each review; Translate HTML descriptions; Translate reviews into English; Translate tickets into English
Autosheet in ExcelExcelSidebar add-onGPT-6 LunaHigh83.415631Add a cover page to an annual report; Build a cover sheet for a project plan; Align zero on a dual-axis combo chart; Build a cash-flow waterfall chart; Show a chart's labels as whole percentages; Make a pie chart of revenue by year; Split two series onto their own axes; Chart traffic sources, then make it a pie; Build an e-commerce KPI dashboard; Add seniority columns in the table's format; Format amounts as US dollars; Add thousands separators; Turn a revenue table into a heatmap; Hide two columns; Make a table look professional; Pivot revenue, cost and margin; Normalize ticket priorities; Extract order IDs from tickets; Find and replace a year in text; Freeze the top row and three columns; Generate 1,000 sample CRM records; Group rows by category; Rewrite product descriptions in place; Sort a table with merged cells; Summarize job descriptions; Summarize reviews in one line; Summarize support tickets; Fix broken formulas and validate amounts; Tag the main theme of each review; Fix numbers stored as text; Translate HTML descriptions
Copilot in ExcelExcelSidebar add-onAutoAuto81.815334Align zero on a dual-axis combo chart; Create a Gantt chart; Create a bar chart labeling only its maximum; Label only the tallest bar of a chart; Label only the latest point of a line; Show a chart's labels as whole percentages; Chart sorted values, source unchanged; Split two series onto their own axes; Chart traffic sources, then make it a pie; Highlight revenues above a threshold; Highlight whole rows above a threshold; Add thousands separators; Hide two columns; Make a table look professional; Categorize support tickets; Classify the sentiment of tickets; Detect salary ranges in job posts; Draft a reply to each review; Extract order IDs from tickets; Find each company's headquarters; Find the INDEX/MATCH formulas; Freeze the top row and three columns; Generate 1,000 sample CRM records; Group rows by category; Normalize company industries; Rewrite product descriptions in place; Sort a table with merged cells; Summarize job descriptions; Summarize support tickets; Fix broken formulas and validate amounts; Translate HTML descriptions; Translate a catalog into English; Translate reviews into English; Translate tickets into English
ChatGPT in ExcelExcelSidebar add-onGPT-6 LunaHigh76.514344Build a cover sheet for a project plan; Add a mini trend chart per product; Align zero on a dual-axis combo chart; Make a donut chart of spend; Plot price against units sold; Create a Gantt chart; Give a chart a proper title; Create a bar chart labeling only its maximum; Label only the latest point of a line; Use a log scale on data with zeros; Show a chart's labels as whole percentages; Make a pie chart of revenue by year; Reverse the order of a chart's bars; Split two series onto their own axes; Add seniority columns in the table's format; Highlight the top 10 values; Highlight revenues above a threshold; Format amounts as US dollars; Add thousands separators; Make a table look professional; Pivot cumulative revenue over time; Pivot revenue by region with % of total; Pivot revenue by region, then filter it; Categorize support tickets; Classify the sentiment of tickets; Draft a reply to each review; Extract order IDs from tickets; Filter rows above a revenue; Filter to one region; Find each company's headquarters; Find and replace a year in text; Write SEO descriptions; Generate 1,000 sample CRM records; Group rows by category; Rewrite product descriptions in place; Sort a table with merged cells; Summarize job descriptions; Summarize reviews in one line; Summarize support tickets; Tag the main theme of each review; Translate HTML descriptions; Translate a catalog into English; Translate reviews into English; Translate tickets into English
Autosheet in SheetsGoogle SheetsSidebar add-onOpus 5.5Medium92.017215Create a Gantt chart; Use a log scale on data with zeros; Make a pie chart of revenue by year; Split two series onto their own axes; Switch a chart's axis to a log scale; Format amounts as US dollars; Add thousands separators; Track what's left of a budget; Pivot cumulative revenue over time; Categorize job titles; Normalize ticket priorities; Set the height of data rows; Summarize support tickets; Fix broken formulas and validate amounts; Translate HTML descriptions
Claude in SheetsGoogle SheetsSidebar add-onOpus 5.5Medium89.816819Label only the tallest bar of a chart; Use a log scale on data with zeros; Make a pie chart of revenue by year; Split two series onto their own axes; Format amounts as US dollars; Add thousands separators; Make a table look professional; Pivot cumulative revenue over time; Categorize support tickets; Classify the sentiment of tickets; Draft a reply to each review; Write SEO descriptions; Generate 1,000 sample CRM records; Rewrite product descriptions in place; Set the height of data rows; Summarize job descriptions; Summarize support tickets; Translate HTML descriptions; Convert a range to a table
Autosheet in SheetsGoogle SheetsSidebar add-onHaiku 5.5High87.216324Align zero on a dual-axis combo chart; Make a donut chart of spend; Create a Gantt chart; Use a log scale on data with zeros; Make a pie chart of revenue by year; Reverse the order of a chart's bars; Chart sorted values, source unchanged; Split two series onto their own axes; Switch a chart's axis to a log scale; Add seniority columns in the table's format; Add in-cell bars to a column; Make a table look professional; Pivot cumulative revenue over time; Classify the sentiment of tickets; Standardize messy countries and revenues; Normalize ticket priorities; Find the cells holding a value; Find and replace a year in text; Generate 1,000 sample CRM records; Group rows by category; Rate the quality of product listings; Set the height of data rows; Fix broken formulas and validate amounts; Translate HTML descriptions
Claude in SheetsGoogle SheetsSidebar add-onHaiku 5.5High84.515829Chart sales stacked by region; Combine revenue bars with a rate line; Create a Gantt chart; Label only the tallest bar of a chart; Label only the latest point of a line; Make a pie chart of revenue by year; Show the value on each bar; Chart the top 10 products plus Other; Format amounts as US dollars; Add thousands separators; Make a table look professional; Pivot revenue, cost and margin; Pivot sales by region and product, ranked; Categorize support tickets; Classify the sentiment of tickets; Draft a reply to each review; Filter rows above a revenue; Find the cells holding a value; Find each company's headquarters; Group rows by category; Rewrite product descriptions in place; Set the height of data rows; Summarize job descriptions; Summarize reviews in one line; Summarize support tickets; Fix broken formulas and validate amounts; Tag the main theme of each review; Translate HTML descriptions; Convert a range to a table
Gemini in SheetsGoogle SheetsSidebar add-onAutoAuto74.914047Find hardcoded numbers among formulas; Model team capacity and hiring needs; Compute SMA, RSI and trading signals; Add a cover page to an annual report; Trace the cells that depend on a cell; Build a cash-flow waterfall chart; Combine revenue bars with a rate line; Create a Gantt chart; Label only the tallest bar of a chart; Use a log scale on data with zeros; Make a pie chart of revenue by year; Reverse the order of a chart's bars; Chart sorted values, source unchanged; Split two series onto their own axes; Switch a chart's axis to a log scale; Chart and polish a sales report; Build an e-commerce KPI dashboard; Band the rows that share a case name; Add in-cell bars to a column; Show numbers as K and M, negatives in red; Make a table look professional; Make a financial report presentation-ready; Count the days since each inquiry; Pivot sales by region and product, ranked; Categorize support tickets; Classify the sentiment of tickets; Draft a reply to each review; Find the INDEX/MATCH formulas; Assign clean product categories; Write SEO descriptions; Generate 1,000 sample CRM records; Group rows by category; Rewrite product descriptions in place; Score companies for customer fit; Set the height of data rows; Summarize job descriptions; Summarize reviews in one line; Summarize support tickets; Break event budgets into line items; Fix broken formulas and validate amounts; Look up and color letter grades; Look up supplier rates and totals; Merge media mentions into one sheet; Tag the main theme of each review; Translate HTML descriptions; Translate a catalog into English; Translate reviews into English
ChatGPT in SheetsGoogle SheetsSidebar add-onGPT-6 AstraMedium62.011671Add a cover page to an annual report; Add a missing legend to a chart; Align zero on a dual-axis combo chart; Turn a chart into a horizontal bar chart; Make a donut chart of spend; Chart the distribution of order sizes; Plot price against units sold; Chart sales stacked by region; Build a cash-flow waterfall chart; Combine revenue bars with a rate line; Create a Gantt chart; Give a chart a proper title; Create a bar chart labeling only its maximum; Label only the tallest bar of a chart; Label a chart's y-axis; Label only the latest point of a line; Use a log scale on data with zeros; Show a chart's labels as whole percentages; Make a pie chart of revenue by year; Reverse the order of a chart's bars; Show the value on each bar; Chart sorted values, source unchanged; Split two series onto their own axes; Switch a chart's axis to a log scale; Chart enrollment, then split it by level; Chart and polish a sales report; Chart revenue by quarter; Chart traffic sources, then make it a pie; Build an e-commerce KPI dashboard; Chart the top 10 products plus Other; Add seniority columns in the table's format; Highlight duplicate email addresses; Highlight the top 10 values; Highlight revenues above a threshold; Highlight whole rows above a threshold; Fit a wide report on an A4 page; Format amounts as US dollars; Add thousands separators; Add a centered title across a table; Make a table look professional; Protect a sheet from edits; Widen and wrap a description column; Wrap overflowing notes; Create and use a named range; Group transactions by month and quarter; Pivot cumulative revenue over time; Pivot revenue, cost and margin; Pivot revenue by region with % of total; Pivot hotel rates and nights by room; Pivot revenue by region, then filter it; Pivot the top 5 products by revenue; Pivot sales by region and product, ranked; Categorize support tickets; Classify the sentiment of tickets; Add checkboxes to a range; Add a dropdown of existing values; Draft a reply to each review; Filter rows above a revenue; Filter to one region; Write SEO descriptions; Generate 1,000 sample CRM records; Group rows by category; Rewrite product descriptions in place; Set the height of data rows; Sort a table with merged cells; Summarize job descriptions; Fix broken formulas and validate amounts; Translate HTML descriptions; Translate reviews into English; Translate tickets into English; Convert a range to a table
ChatGPT in SheetsGoogle SheetsSidebar add-onGPT-6 LunaHigh57.210780Add a missing legend to a chart; Align zero on a dual-axis combo chart; Turn a chart into a horizontal bar chart; Make a donut chart of spend; Chart the distribution of order sizes; Plot price against units sold; Chart sales stacked by region; Build a cash-flow waterfall chart; Combine revenue bars with a rate line; Create a Gantt chart; Give a chart a proper title; Create a bar chart labeling only its maximum; Label only the tallest bar of a chart; Label a chart's y-axis; Label only the latest point of a line; Use a log scale on data with zeros; Show a chart's labels as whole percentages; Make a pie chart of revenue by year; Reverse the order of a chart's bars; Show the value on each bar; Chart sorted values, source unchanged; Split two series onto their own axes; Switch a chart's axis to a log scale; Chart enrollment, then split it by level; Chart and polish a sales report; Chart revenue by quarter; Chart traffic sources, then make it a pie; Build an e-commerce KPI dashboard; Chart the top 10 products plus Other; Add seniority columns in the table's format; Add in-cell bars to a column; Highlight the top 10 values; Clear all formatting, keep the data; Highlight revenues above a threshold; Highlight whole rows above a threshold; Fit a wide report on an A4 page; Format amounts as US dollars; Add thousands separators; Add a centered title across a table; Make a table look professional; Protect a sheet from edits; Widen and wrap a description column; Wrap overflowing notes; Create and use a named range; Group transactions by month and quarter; Pivot cumulative revenue over time; Pivot revenue, cost and margin; Pivot revenue by region with % of total; Pivot hotel rates and nights by room; Pivot revenue by region, then filter it; Pivot the top 5 products by revenue; Pivot sales by region and product, ranked; Categorize support tickets; Classify the sentiment of tickets; Add checkboxes to a range; Add a dropdown of existing values; Detect salary ranges in job posts; Draft a reply to each review; Extract order IDs from tickets; Filter rows above a revenue; Filter to one region; Find each company's headquarters; Find and replace a year in text; Write SEO descriptions; Generate 1,000 sample CRM records; Group rows by category; Rewrite product descriptions in place; Set the height of data rows; Sort a table with merged cells; Summarize job descriptions; Summarize reviews in one line; Summarize support tickets; Fix broken formulas and validate amounts; Tag the main theme of each review; Fix numbers stored as text; Translate HTML descriptions; Translate a catalog into English; Translate reviews into English; Translate tickets into English; Convert a range to a table
Claude Code + Sheets MCPGoogle SheetsAI assistant + MCPOpus 5.5Medium89.816819Make a donut chart of spend; Build a cash-flow waterfall chart; Create a Gantt chart; Label only the latest point of a line; Use a log scale on data with zeros; Make a pie chart of revenue by year; Split two series onto their own axes; Switch a chart's axis to a log scale; Format amounts as US dollars; Add thousands separators; Make a table look professional; Pivot cumulative revenue over time; Filter rows above a revenue; Write SEO descriptions; Generate 1,000 sample CRM records; Rewrite product descriptions in place; Score companies for customer fit; Summarize job descriptions; Translate HTML descriptions
Claude Code + Autosheet MCPGoogle SheetsAI assistant + MCPOpus 5.5Opus 5.5Medium88.816621Align zero on a dual-axis combo chart; Make a donut chart of spend; Build a cash-flow waterfall chart; Create a Gantt chart; Create a bar chart labeling only its maximum; Label only the latest point of a line; Use a log scale on data with zeros; Make a pie chart of revenue by year; Split two series onto their own axes; Switch a chart's axis to a log scale; Format amounts as US dollars; Add thousands separators; Make a table look professional; Count the days since each inquiry; Categorize job titles; Categorize support tickets; Normalize ticket priorities; Filter rows above a revenue; Generate 1,000 sample CRM records; Rate the quality of product listings; Flag abnormal patient vitals
ChatGPT + Autosheet MCPGoogle SheetsAI assistant + MCPGPT-6Opus 5.5Medium87.216324Compute SMA, RSI and trading signals; Create a Gantt chart; Create a bar chart labeling only its maximum; Label only the tallest bar of a chart; Use a log scale on data with zeros; Make a pie chart of revenue by year; Split two series onto their own axes; Switch a chart's axis to a log scale; Add seniority columns in the table's format; Format amounts as US dollars; Add thousands separators; Make a table look professional; Count the days since each inquiry; Pivot cumulative revenue over time; Categorize support tickets; Filter rows above a revenue; Find each company's headquarters; Generate 1,000 sample CRM records; Rewrite product descriptions in place; Set the height of data rows; Fix broken formulas and validate amounts; Flag abnormal patient vitals; Tag the main theme of each review; Convert a range to a table
ChatGPT + Drive MCPGoogle SheetsAI assistant + MCPGPT-6Medium81.815334Add a cover page to an annual report; Align zero on a dual-axis combo chart; Turn a chart into a horizontal bar chart; Make a donut chart of spend; Create a Gantt chart; Label only the tallest bar of a chart; Label only the latest point of a line; Use a log scale on data with zeros; Make a pie chart of revenue by year; Reverse the order of a chart's bars; Split two series onto their own axes; Switch a chart's axis to a log scale; Build an e-commerce KPI dashboard; Format amounts as US dollars; Add thousands separators; Make a table look professional; Pivot cumulative revenue over time; Categorize job titles; Categorize support tickets; Classify the sentiment of tickets; Detect salary ranges in job posts; Draft a reply to each review; Extract order IDs from tickets; Write SEO descriptions; Generate 1,000 sample CRM records; Rewrite product descriptions in place; Rate the quality of product listings; Summarize job descriptions; Summarize reviews in one line; Summarize support tickets; Fix broken formulas and validate amounts; Tag the main theme of each review; Translate HTML descriptions; Translate a catalog into English

Strengths and weaknesses

Where each product shines, where it slips, and what the scores don't show, on its best model.

Each product's strengths, weaknesses and quirks on its best model, grouped by kind of product.
Product / modelStrongWatch out forGood to know
Excel · Sidebar add-ons
Autosheet in ExcelOpus 5.5 (Medium)
The most consistent: first or tied first in six of eight capabilities, and far ahead on bulk content generation.Bulk results might depend on the model chosen for the bulk run.—
Claude in ExcelOpus 5.5 (High)
Near perfect on formulas, structural edits and data operations, and reliable charts.Lower bulk content generation quality. It writes every row itself: long jobs are slow, can stop partway and use templates.Often asks permission to keep a long script running: about one task in five.
ChatGPT in ExcelGPT-6 Astra (Medium)
Strong on formulas and data operations.Fixed formats and edits instead of conditional rules or filters. Slow, templated content generation.—
Copilot in ExcelAuto
Passes every pivot table task, and is faster than Claude and ChatGPT in Excel.Several weaknesses: templated content generation, quotas on translations. It misses fine chart details.Copilot picks the model; there is no choice.
Google Sheets · Sidebar add-ons
Autosheet in SheetsOpus 5.5 (Medium)
Best in Google Sheets. The best add-on at bulk content generation, and at the top on native spreadsheet work.—Only Claude in Sheets passed one of the two log-scale chart tasks in Google Sheets, while every product passed both in Excel.
Claude in SheetsOpus 5.5 (Medium)
The same strong native spreadsheet work as in Excel.Slow and low quality bulk content generation, as in Excel. Charts are less reliable than in Excel.Asks before running some scripts. A request left unanswered stalls the task.
Gemini in SheetsAuto
Data operations and simple structural edits.The slowest, at over two minutes per task. It passes one bulk content generation task in eleven.Low monthly AI credits: finishing the benchmark took a second month (they renew on the 1st) and an upgrade.
ChatGPT in SheetsGPT-6 Astra (Medium)
Formulas.No native charts or pivot tables: it draws text bars and formula summaries instead. Passes half the formatting tasks.—
Google Sheets · AI assistant + MCP
Claude Code + Sheets MCPOpus 5.5 (Medium)
Good native spreadsheet work through a general-purpose coding agent.Slow, often over a minute per task, and middling on bulk content generation.Better than the Claude add-ons at bulk content generation, by spawning subagents that work in parallel.
Claude Code + Autosheet MCPOpus 5.5 (Medium)
Handing bulk work to Autosheet does better on bulk content than the Sheets MCP.Slower than Autosheet in Sheets, often over a minute per task, due to the back-and-forth between the two assistants.Claude Code asks you to approve the Autosheet tool on many tasks.
ChatGPT + Autosheet MCPGPT-6 (Medium)
Strong on data operations. Far ahead of ChatGPT + Drive MCP on bulk work, and ahead on charts.Bulk tasks still depend on the bulk model. Risk of a “telephone game” effect between ChatGPT and the Autosheet agent.—
ChatGPT + Drive MCPGPT-6 (Medium)
Strong on formulas and structural edits.Weak on bulk work on long datasets, both on data processing and content generation.Rebuilds charts rather than editing them, without carrying over every setting: they can lose their colors.

Head to head

Pick two products to see where each one wins, capability by capability and task by task.

Compare configuration
VS
With configuration
255075100Formulas(n=42)Spreadsheetmanipulation(n=36)Charts(n=30)Data operations(n=17)Formatting(n=26)Pivot tables(n=8)Bulk contentgeneration(n=11)Bulk dataprocessing(n=17)Autosheet in Excel: Formulas 100.0%Autosheet in Excel: Spreadsheet manipulation 100.0%Autosheet in Excel: Charts 96.7%Autosheet in Excel: Data operations 100.0%Autosheet in Excel: Formatting 96.2%Autosheet in Excel: Pivot tables 87.5%Autosheet in Excel: Bulk content generation 100.0%Autosheet in Excel: Bulk data processing 88.2%Copilot in Excel: Formulas 100.0%Copilot in Excel: Spreadsheet manipulation 91.7%Copilot in Excel: Charts 70.0%Copilot in Excel: Data operations 88.2%Copilot in Excel: Formatting 80.8%Copilot in Excel: Pivot tables 100.0%Copilot in Excel: Bulk content generation 18.2%Copilot in Excel: Bulk data processing 64.7%

Compare the outputs

Or select a capability on the chart.

AutosheetBench head to head: Autosheet in Excel (Opus 5.5) versus Copilot in Excel (Auto), by capability, on those of the 187 tasks scored for both. Latest run November 17, 2026.
CapabilityTasks comparedAutosheet in Excel (Opus 5.5, Medium) score (%)Copilot in Excel (Auto) score (%)Autosheet in Excel (Opus 5.5, Medium) winsCopilot in Excel (Auto) winsBoth passedBoth failed
Formulas42100.0100.000420
Spreadsheet manipulation36100.091.730330
Charts3096.770.091200
Data operations17100.088.220150
Formatting2696.280.840211
Pivot tables887.5100.00170
Bulk content generation11100.018.29020
Bulk data processing1788.264.751101
All capabilities18797.381.83231502

Selected examples

Pick an example to see the prompt, the starting spreadsheet and what each product made of it.

The task

Task files
Prompt

Create a Gantt chart.

Starting spreadsheetData
ABC
1TaskStart DateDuration (days)
2Plan2025-04-013
3Design2025-04-035
4Build2025-04-088
5QA2025-04-144
6Launch2025-04-192
7Training2025-04-203
8Review2025-04-242
9Wrap-up2025-04-261
Expected result

The outputs

3 of 12 passRun files
Excel and Sheets · All types · Best models · All outputs
Pass criteriaAll must be met, checked by an LLM judge.
  • A horizontal bar chart
  • Only the task blocks are colored
  • Readable dates in order
  • A clear title; any legend at the top

Passed 3

Autosheet in Excel Opus 5.5 · Medium
Passed46s · 16¢
Claude in Excel Opus 5.5 · High
Passed51s · 27¢
Claude in Sheets Opus 5.5 · Medium
Passed42s · 17¢

Failed 9

Autosheet in Sheets Opus 5.5 · Medium
Failed45s · 12¢

Why it failed: The horizontal axis shows day numbers ('0', '10', '20', '30') labeled 'Days from project start' instead of readable calendar dates.

Claude Code + Sheets MCP Opus 5.5 · Medium
Failed59s · N/A

Why it failed: The horizontal axis shows numeric increments (0, 10, 20, 30) rather than dates.

Claude Code + Autosheet MCP Opus 5.5 · Medium
Failed1m 42s · N/A

Why it failed: The horizontal axis shows numeric day offsets rather than readable dates.

ChatGPT + Autosheet MCP GPT-6 · Medium
Failed1m 37s · N/A

Why it failed: No chart object was created (chartCount is 0).

ChatGPT in Excel GPT-6 Astra · Medium
Failed2m 45s · $1.37

Why it failed: The horizontal axis counts days from the start, 0 to 28, instead of showing dates.

Copilot in Excel Auto
Failed1m 26s · N/A

Why it failed: Floating Gantt blocks were not formed; standard solid bars originate from the vertical axis.

ChatGPT + Drive MCP GPT-6 · Medium
Failed54s · N/A

Why it failed: The horizontal axis displays numeric offsets (0, 10, 20, 30) rather than readable dates.

Gemini in Sheets Auto
Failed3m 2s · N/A

Why it failed: The horizontal axis plots numeric day offsets (=B2-$B$2) rather than readable calendar dates.

ChatGPT in Sheets GPT-6 Astra · Medium
Failed1m 1s · 57¢

Why it failed: No chart was created.

Browse the full dataset

Check out all 187 tasks in detail. Click on any task to zoom in.

Skip the 187 tasks

187 tasks

Every task and run is also in the AutosheetBench dataset on Hugging Face.

How we built the tasks

AutosheetBench runs mostly on synthetic data, modeled on the Autosheet usage of thousands of users: 166 of its 187 tasks. The other 21 start from real data, public or anonymized, with names and identifiers replaced.

  • Real use cases

    The benchmark covers what people ask Autosheet to do in Excel and Google Sheets. We analyzed tens of thousands of anonymized Autosheet conversations and broke their requests into unit tasks.

  • Realistic human prompts

    We wrote every prompt for the benchmark, short and direct like our users' own. They don't spell out every requirement the way an AI would. What the person asking would expect is in the pass criteria, not the prompt.

  • Synthetic data, real variety

    The workbooks are synthetic: generated from anonymized conversations, then adjusted by hand. Some start from real data, public or anonymized, with names and identifiers replaced.

  • Pass criteria edited by hand

    An LLM judge grades the tasks whose result can take several forms. Every checkpoint of its checklist was edited by hand to match what users expect.

How each task is scored

Every task is pass or fail, with no partial credit. We use deterministic checks, LLM judges and, for bulk tasks, whole-set checks.

  • Deterministic checks

    96 native tasks

    We compare the workbook with the expected final state (values, formulas, rules and more). A single miss fails the task. When a task can be done more than one right way, each way is accepted.

  • LLM judge with a checklist

    63 native tasks

    When the result could take several forms (a chart, a cover sheet, an answer in the chat), an LLM judge grades the final workbook, screenshots of it and the transcript against a checklist. One missed checkpoint fails the task.
    We used Gemini 3.8 Flash as judge.

  • Whole-set checks

    28 bulk tasks

    In bulk tasks, every row must be filled and follow the prompt's rules (e.g., a maximum length or a fixed list of values): at least 98% of rows must match when each row has one right answer, and three tasks require every row. When answers can vary (translation, SEO description, etc.), an LLM judge also grades 50 sampled rows, and 45 must pass. Generated text must also vary: a task fails when 10 or fewer templates (sentence patterns reused from row to row) cover 80% of the rows, and a generated dataset fails when the judge finds its entries repeated or combined from a few reused words.

Criteria calibrated to real-life expectations

Numbers must be readable. Presentation must be intuitive. Generated text must be high quality.

Numbers must be readable

Right values aren't enough. We also check formats, rules, charts and how the sheet renders. A number hidden behind ###### or cut off by its column fails, even when the value is right.

How it's checked: LLM judge with a checklist

Columns wide enough to read
Prompt

Add thousands separators to the big numbers.

The separators are there, but column B is too narrow: ###### hides two of the numbers.

The column fits, so every number reads in full.

See all outputs

Presentation must be intuitive

Prompts are short, the way people write them. We grade what the person asking would expect, not only what the prompt spells out. Every checklist, accepted answer and quality criterion was calibrated that way.

How it's checked: LLM judge with a checklist

A plan reads by dates
Prompt

Create a Gantt chart.

The bars are right, but the axis counts days from the start: 0, 2, 4, 6.

The axis shows dates, which is what a project plan reads by.

See all outputs

High quality generated text

Generated text, such as a summary, a translation or a product description, can follow every rule and still be wrong. An LLM judge reads a sample of rows against their source. A row fails if a careful person could easily make it more accurate, complete or useful.

How it's checked: Whole-set checks

Summaries true to the source
Prompt
Summarize each job description in column C (job_description). Add a new column with the header job_summary in column F. Write a clear one-line summary of at most 160 characters describing the role's main purpose and responsibilities. Do not copy the full description and fill every row.
One job description

…extracting actionable insights to help empower businesses to better manage their fleets.

Rejected

Lead teams and projects, build machine-learning models, and analyze complex data to improve healthcare decisions.

Nothing in the job is about healthcare. Copilot reused one boilerplate: 845 of its 1,000 summaries start with “Lead teams and projects”.

Accepted

Develop machine learning models and statistical tools from connected-vehicle data to improve fleet insights and transportation decisions.

Specific to the job: vehicle data, used to serve fleets.

See all outputs

FAQ

How we ran AutosheetBench's 187 tasks, judged them, timed them and measured cost.

What are the tasks?

Each task is one request a user would make to a spreadsheet assistant: a workbook, a prompt and the final state we check. We built them by breaking real, anonymized requests into single steps, each on a workbook: synthetic for most tasks, real data with identifiers replaced for 21 of them (see How we built the tasks). 22 tasks add a scripted follow-up prompt, sent once the assistant finishes the first.

CategoryTasksFor example
Formulas42Writing formulas, tracing dependents
Spreadsheet manipulation36Hiding, deleting, or inserting rows and columns
Charts30Creating and updating charts
Data operations17Trimming, find and replace, filling blanks, finding specific cells
Formatting26Conditional formatting, number formats
Pivot tables8Creating pivot tables
Bulk content generation11Translating text, writing SEO descriptions, summarizing reviews
Bulk data processing17Extracting a salary from a job description, cleaning or standardizing data, classifying the sentiment of reviews

Each task starts from a fresh copy of its workbook and must be finished within 5 minutes. The 26 long bulk tasks, which fill up to 1,000 rows, get 10 minutes.

Every task passes or fails. Of the 159 native tasks, 96 are checked deterministically against the expected final state, and 63 by an LLM judge with a checklist, 6 of them on an exact answer. The 28 bulk tasks get whole-set checks, deterministic checks that every row is filled and follows the prompt's rules: 14 by those checks alone, and the 14 whose answers can vary, such as translations, by those checks and a quality judge that grades 50 sampled rows (see How each task is scored). 8 of the 4,114 results were scored by hand, mostly where a Google Sheets export loses what the assistant did (a sheet's protection, its checkboxes); the dataset marks each one with its reason.

How do the LLM judges work?

The checklist judge

The checklist judge scores 63 of the native tasks: those where a script can't tell whether the result is right, such as a chart or a pivot table, or where the answer is in the assistant's reply rather than in the sheet. The task passes only if every checkpoint passes.

It runs Gemini 3.8 Flash through OpenRouter, at medium effort, and judges each output once. Judging all 1,386 outputs cost $12.44, about 1¢ each. Each task's page shows a short version of its checklist.

Its system prompt for a task without charts:

You evaluate whether a spreadsheet agent fulfilled a user's spreadsheet request. You will receive: - the authored user request - a structured scoring rubric with weighted control points - a full transcript - actual spreadsheet images - expected images when available - workbook summaries Use the authored user request and rubric to define success. Final artifacts are the primary source of truth for the final result. Do not treat the transcript as proof that a step succeeded unless the final artifacts support it. Prefer image/workbook evidence over transcript when judging the final state. Be strict, concise, and evidence-based. Respond with JSON only.

For a task with charts, the same prompt gets chart and document details instead of workbook summaries:

You evaluate whether a spreadsheet agent fulfilled a user's spreadsheet request. You will receive: - the authored user request - a structured scoring rubric with weighted control points - a full transcript - actual spreadsheet images - expected images when available - chart/document payload metadata Use the authored user request and rubric to define success. Final artifacts are the primary source of truth for the final result. Do not treat the transcript as proof that a step succeeded unless the final artifacts support it. Prefer image/workbook evidence over transcript when judging the final state. Be strict, concise, and evidence-based. Respond with JSON only.

For a task where every checkpoint is about the assistant's reply, the judge gets only the prompt, the checklist and the transcript, with this system prompt:

You evaluate whether a spreadsheet agent correctly answered a user's spreadsheet question. Use only the authored user request, rubric, and transcript supplied to you. Do not inspect, infer from, or score any workbook summary, spreadsheet image, or output workbook state. Be strict, concise, and evidence-based. Respond with JSON only.

The quality judge

The quality judge scores the 14 bulk tasks whose answers can vary, such as translations, summaries or product descriptions. The quality judge reads a sample of 50 rows of the bulk output, and passes or fails each row against the task's quality bar. It sees the prompt, the 50 rows, the quality bar and the rule for passing. The task passes if at least 45 of the 50 rows pass and the deterministic checks pass too. For the one task that generates a dataset, the judge also grades the dataset as a whole, which fails when its entries repeat or are combined from a few reused words. Three tasks that generate text also fail if 10 or fewer templates (sentence patterns reused from row to row) write 80% of the rows: a script checks this, not the judge.

It runs Gemini 3.8 Flash through OpenRouter, at high effort and temperature 0, and judges each output once. It needs high effort because it has no checklist to follow: at medium, it let real errors through. Judging all 308 outputs cost $26.20, about 9¢ each. Each task's page shows its quality bar and its rule for passing.

Its prompt, below, is a single message, with each task's own parts in brackets.

You are a strict independent quality-control reviewer. Judge one anonymous spreadsheet submission against the task. Review every row independently and return a binary PASS or FAIL for each row. Do not assign numeric quality scores and do not compare the output to any other product. TASK: [the task's prompt] QUALITY BAR: - [one line per criterion of the task's quality bar] [the task's decision rule] For every row FAIL, name the concrete correction. For PASS rows, return an empty reason and an empty issues array. Do not spend output tokens explaining acceptable rows. Return JSON only in exactly this shape: {"caseId":"[the task's id]","rows":[{"sampleId":"row-2","pass":true,"reason":"brief, specific evidence","issues":["short_issue_code"]}],"batchRationale":"brief overall pattern"} Return exactly one decision for every supplied sample ID. Keep each FAIL reason under 25 words. SAMPLES: [the 50 sampled rows, each with its source columns and the output]

Why are we comfortable using Gemini 3.8 Flash to judge stronger models?

  • Calibrated on human expectations. We tested the judge and its effort level, and checked that its verdicts agree with human judgement.
  • Checking is easier than doing. The judge doesn't solve the task: it compares the output with what is expected, validating it against a strict checklist.
  • It is independent of most products. It comes from neither Anthropic nor OpenAI, whose models run most of the products here, so it has no reason to prefer the style of the text they write.
  • It keeps judging costs reasonable. Judging every output on this page once cost ~$39 on OpenRouter. Opus 5.5 would have cost about five times as much for the same tokens, some $210.

Which products, models and effort levels did we test?

ProductModelEffort
Excel · Sidebar add-ons
Autosheet in ExcelOpus 5.5Medium
Sonnet 5.5Medium
Haiku 5.5High
GPT-6 AstraLow
GPT-6.1 SolMedium
GPT-6 LunaHigh
Claude in ExcelOpus 5.5High
Haiku 5.5High
ChatGPT in ExcelGPT-6 AstraMedium
GPT-6 LunaHigh
Copilot in ExcelAutoAuto
Google Sheets · Sidebar add-ons
Autosheet in SheetsOpus 5.5Medium
Haiku 5.5High
Claude in SheetsOpus 5.5Medium
Haiku 5.5High
Gemini in SheetsAutoAuto
ChatGPT in SheetsGPT-6 AstraMedium
GPT-6 LunaHigh
Google Sheets · AI assistant + MCP
Claude Code (web) + Sheets MCPOpus 5.5Medium
Claude Code (web) + Autosheet MCPOpus 5.5 · MCP runs Opus 5.5Medium · MCP Medium
ChatGPT (web) + Autosheet MCPGPT-6 · MCP runs Opus 5.5Medium · MCP Medium
ChatGPT (web) + Drive MCPGPT-6Medium

How each model and its effort level were set:

  • Autosheet: for each model, the level with the best quality-to-cost ratio on the internal benchmark we use to recommend settings.
  • Copilot and Gemini choose their model and effort level themselves and don't show them: the page reads Auto.
  • ChatGPT on the web, in the two ChatGPT + MCP configurations, doesn't say which model answers: the page reads GPT-6.
  • The other products: the model closest to an Autosheet configuration (Opus 5.5 in Claude, GPT-6 Astra in ChatGPT in Excel), at the product's default or recommended effort level. In Excel and Google Sheets, Claude also ran Haiku 5.5 and ChatGPT ran GPT-6 Luna, matching two more Autosheet configurations.

What is AI cost and how is it computed?

AI cost is what a run's model calls cost at the AI providers' API list prices: the tokens each call used, and the web searches.

What you really pay depends greatly on the plan you're on, as each product and plan takes a different margin on the API prices. That's why we compare the API cost: it's the only objective cost we can track. Claude's and ChatGPT's subscriptions in particular end up far cheaper than their API cost: a $25 Standard seat of either holds a whole run of all 187 tasks, 13¢ a task, while their heaviest runs cost 35¢ and 80¢ a task at API list prices (see How much does it cost to run the full benchmark?).

How the AI cost is computed

From the tokens recorded for each model call, at the providers' API list prices of November 2026.

Model, per million tokensInputCache write5m on Claude30m on OpenAICache readOutputWeb searchper 1,000
Claude Opus 5.5$4$5$0.20$20$10
Claude Sonnet 5.5$2$2.50$0.10$10$10
Claude Haiku 5.55× on a prompt over 100,000 tokens$0.10$0.125$0.01$0.50$10
GPT-6 Astra$10$12.50$1$50$10
GPT-6.1 Sol$2$2.50$0.10$10$10
GPT-6 Luna$0.10$0.125$0.01$0.50$10
Perplexity FastBulk only · Agent API (GPT-5.6 Luna underneath)$0.20$0.25$0.02$1.20$2.50

Autosheet runs every OpenAI model but GPT-6 Astra on the priority tier (prices ×2). ChatGPT's and Claude's add-ons run on the standard tier.

Autosheet's bulk rows run on GPT-6 Luna. A few tasks in seven configurations called the bulk model before the switch; their tokens are priced at GPT-6 Luna's rates (under 7 cents per configuration).

We couldn't record Copilot's and Gemini's token usage. The charts show their plan's month instead. We couldn't compute the API usage of the assistants on an MCP either, so those configurations have no AI cost.

How much does it cost to run the full benchmark?

The cheapest plan that holds one run of all 187 tasks within a month, at its US monthly price (billed monthly). Prices don't include the Microsoft 365 or Google Workspace subscription for Excel or Sheets itself.

For Autosheet: it's the Standard plan ($25, $25 of usage included), plus the cheapest extra-usage packs ($29, $79, $139, $299, $999) if needed.

ConfigurationPlanMonth
Gemini in Sheets · AutoGoogle Workspace AI Expanded Access$24
Claude in Excel · Opus 5.5Claude Team – Standard seat$25
Autosheet in Excel · Haiku 5.5Autosheet Standard$25
Claude Code + Sheets MCP · Opus 5.5Claude Team – Standard seat$25
Claude in Sheets · Opus 5.5Claude Team – Standard seat$25
ChatGPT in Excel · GPT-6 AstraChatGPT Business – Standard seat$25
Claude in Excel · Haiku 5.5Claude Team – Standard seat$25
ChatGPT + Drive MCP · GPT-6ChatGPT Business – Standard seat$25
ChatGPT in Excel · GPT-6 LunaChatGPT Business – Standard seat$25
ChatGPT in Sheets · GPT-6 AstraChatGPT Business – Standard seat$25
Copilot in Excel · AutoMicrosoft 365 Copilot (Premium)$31.50
Autosheet in Excel · Opus 5.5Autosheet Standard + $29 usage$54
Autosheet in Excel · GPT-6 AstraAutosheet Standard + $29 usage$54
Autosheet in Excel · Sonnet 5.5Autosheet Standard + $29 usage$54
Autosheet in Excel · GPT-6.1 SolAutosheet Standard + $29 usage$54
Autosheet in Sheets · Haiku 5.5Autosheet Standard + $29 usage$54
Autosheet in Excel · GPT-6 LunaAutosheet Standard + $29 usage$54
Autosheet in Sheets · Opus 5.5Autosheet Standard + $58 usage$83
Claude Code + Autosheet MCP · Opus 5.5Claude Team – Standard seat + Autosheet Standard + $79 usage$129
ChatGPT + Autosheet MCP · GPT-6ChatGPT Business – Standard seat + Autosheet Standard + $79 usage$129

A Claude Team or ChatGPT Business Standard seat holds every run, by the usage history of the seats the runs used: a Claude Standard month holds at least $226 of API-equivalent usage and a ChatGPT one about $602, while the heaviest runs need $66 and $150.

How did we run and record the tasks?

How we run the tasks

A script, the runner, runs every task the same way:

  1. Open a fresh copy of the workbook
  2. Start the screen recording
  3. Send the prompt
  4. Grant any permission the assistant asks for, then wait for it to finish
  5. Send the follow-up, if any
  6. Save the workbook and the transcript

In Excel, the runner drives the add-on through macOS accessibility. In Google Sheets and for the assistants connected through an MCP, it drives Chrome through computer use, an AI agent that operates the screen and follows the same steps, with the chat beside the sheet so the recording shows both. A few Excel runs used computer use too.

When a run doesn't go to plan

  • We discard runs that fail for a reason outside the product and run them again from a fresh copy. That covers a network error, credits or a usage cap running out, and a model at capacity. We also run a task again when the task itself changed: its input or its prompt. We score the first run that ends cleanly, never the best of several.
  • When an assistant stops to ask a question, we send one fixed reply: keep going and complete the original task, using your best judgment for any remaining choices. We never add facts or hints. The time it waits counts toward the time limit.
  • We stop a run at its time limit and score the workbook as it is. The limit is 5 minutes, or 10 for the long bulk tasks. 44 of the 4,114 runs reached it, and 5 of them still pass.

What we keep from each run

From one run, Claude in Excel with Opus 5.5 on the “Chart sales stacked by region” task:

  • Screen recordingThe whole run, the sheet beside the chat
  • TranscriptThe product's own export where it has one
  • chart_stacked_bar_output.xlsx
    Output workbookSaved as the run left it
  • Output screenshotTaken after the run, cropped to the result
  • Duration
    9.2 s
    Turns
    1
    Approvals
    0
    Questions
    0
    Timings, approvals and questionsClaude's session time, checked on the recording

How duration is computed

We time each run from the moment the prompt is sent to the end of the answer, added up over its turns, so the runner's time to send a follow-up doesn't count. Most runs are timed on their screen recording, frame by frame. Autosheet's durations come from its own logs, which we checked against its recordings: they agree within 2 seconds. Its runs without a log are timed on their recording like the others. Claude in Excel's with Opus 5.5 come from Claude's usage dashboard, its session time, which agrees with its recordings within a second on 181 of its 187 tasks; the other 6 are cut off at their time limit. Claude in Excel's with Haiku 5.5, and a few runs of ChatGPT and Claude in Sheets, come from the product's own timing. When a Claude add-in asks permission to run a script, the time its card waits for our click is measured on the recording and taken out.

Where no recording shows the end of a turn, the runner's clock times the run: 138 Copilot runs, and 63 runs of the other assistants, most of them connected through the Autosheet MCP. It notices the end of a turn late, so those durations are upper bounds.

What setup did we use?

  • MachineMacBook Pro 14-inchApple M5 Pro chip, 48 GB of memorymacOS Tahoe (26)
  • ExcelExcel for MacThe desktop app, kept up to dateIn French (fr-FR)
  • Google SheetsGoogle ChromeOn the same Mac
  • Claude CodeClaude Code on the webclaude.ai/code, in ChromeFor the MCP runs
  • ChatGPTChatGPT on the webchatgpt.com, in ChromeFor the MCP runs

We always use the latest version of each product, which changes frequently. At the time of writing, the Mac runs macOS 26.7.2 and Excel is version 16.114.1.

How can I verify these results?

Every run is on Hugging Face, in the AutosheetBench dataset: each task's starting workbook, prompts, expected result and pass criteria, and each configuration's output workbook and transcript. Most runs also have their screen recording, which is what lets us time a run precisely, and which shows exactly what the assistant did when you want to check a verdict yourself.

Anyone can score the outputs again with the scoring script in the AutosheetBench repo: give it a task and an output workbook, and it says whether the output passes.

How can I run the benchmark myself?

Everything you need is on GitHub, in the AutosheetBench repo: the 187 tasks, the instructions for running them, and the scripts that run and score them. You can run a few tasks or all of them.

The easiest way to start is to point an AI agent at the repo and ask it to run one task.

Cite AutosheetBench

If AutosheetBench is useful for your research or writing, please cite it. Every configuration's scores, task results and each run's AI cost and duration are also available as CSV files. The tasks, the scorer and the runner are on GitHub, and every result with its evidence is on Hugging Face. The tasks (prompts, workbooks and checks) and the scores are licensed under CC BY 4.0, except the job postings, the product listings, the rewritten app reviews and two SpreadsheetBench-v2 workbooks (MIT). The products' answers, workbooks, transcripts, screenshots and recordings are not covered.

Earlier runs are described in Best Excel AI models: Introducing AutosheetBench (October 6, 2026) and Best Excel AI add-ins: Autosheet vs Claude vs ChatGPT vs Copilot (October 26, 2026).

AutosheetBench: Benchmarking Excel and Sheets AINicolas Augusti and Stanislas Marion · November 2026Contact: nicolas.augusti@talarian.io · stan@talarian.io

BibTeX
@misc{autosheetbench2026,
  title        = {{AutosheetBench}: Benchmarking Excel and Sheets {AI}},
  author       = {Augusti, Nicolas and Marion, Stanislas},
  organization = {Talarian},
  year         = {2026},
  month        = nov,
  url          = {https://autosheet.com/benchmark},
  note         = {Latest run November 17, 2026},
}