PodcastIntelligence Snacks · Weekly conversations about AI, software and business, from the team behind Normie Mode.Listen →
Best AI for…

Best AI for Excel and spreadsheets

Asking questions about your data, cleaning up sheets, formulas and summaries.

Best overall

Claude Fable 5.1

Get it with Claude Max, $100 a month (for up to half your weekly allowance)

Top of 8 models for this task

Best for $25 a month or lessToo close to call
  • GPT-6 AstraGet it with ChatGPT Plus, $20 a month (only in ChatGPT's Work mode and Codex, not normal chat)
  • Gemini 3.8 FlashGet it with Google AI Pro, $19.99 a month

2nd and 3rd of 8 models for this task

Best free

Claude Sonnet 5

Get it with Claude Free

4th of 8 models for this task

Keep in mind Nothing here yet tests working inside real Excel files, only answering questions about the data.

Based on tests of this task. The picks follow a fixed rule using the charts below and each app's plans.

Already paying for one? See what each plan gives you here
App and planPriceBest model on it for thisPosition
ChatGPT FreefreeNo score yet
Its main model, GPT-5.6 Luna, is too new to score yet.
–
ChatGPT Go$8 a monthNo score yet
Its main model, GPT-5.6 Luna, is too new to score yet.
–
ChatGPT Plus$20 a monthGPT-6 Astra
Only in ChatGPT's Work mode and Codex, not normal chat
Its main model, GPT-5.6 Sol, is too new to score yet.
2nd of 8
ChatGPT Pro$100 a monthGPT-6 Astra
Called GPT-6 Pro in the app
2nd of 8
Claude FreefreeClaude Sonnet 54th of 8
Claude Pro$20 a monthClaude Sonnet 5
Its main model, Claude Opus 5.5, is too new to score yet.
4th of 8
Claude Max$100 a monthClaude Fable 5.1
For up to half your weekly allowance
Its main model, Claude Opus 5.5, is too new to score yet.
1st of 8
Gemini FreefreeGemini 3.6 Flash6th of 8
Google AI Plus$4.99 a monthGemini 3.6 Flash6th of 8
Google AI Pro$19.99 a monthGemini 3.8 Flash3rd of 8
Google AI Ultra$99.99 a monthGemini 3.8 Flash3rd of 8
Kimi FreefreeKimi K37th of 8
Kimi Moderato$19 a monthKimi K37th of 8

Norm's guide

What I'd tell a friend who asked.

What AI is good at

  • Answering questions about your data, like totals, top customers and trends.
  • Writing and explaining formulas.
  • Turning a messy export into a tidy table.

Where it trips up

  • Missing part of a sheet, or adding up the wrong rows.
  • Quietly counting things you'd have left out, like refunds or cancelled orders.
  • Very large files, where it may only look at part of the data.

How to get a good result

  • Tell it your rules up front, for example 'only count completed orders'.
  • Ask it to show which rows it used.
  • Check one number you already know before trusting the rest.

How the models compare

Every model we could score for Excel and spreadsheets, combining the tests below.

Overall for Excel and spreadsheets

Position on a combined score from 3 tests. The longer the bar, the further ahead · Higher is better

On the tests we have, Claude Fable 5.1 comes out on top, followed by GPT-6 Astra and Gemini 3.8 Flash.

Claude Fable 5.1 · Anthropic1st
GPT-6 Astra · OpenAI2nd
Gemini 3.8 Flash · Google DeepMind3rd
Claude Sonnet 5 · Anthropic4th
DeepSeek V4 Pro · DeepSeek5th
Gemini 3.6 Flash · Google DeepMind6th
Kimi K3 · Moonshot AI7th
Gemini 3.1 Pro · Google DeepMind8th

The evidence

Answering business questions from a spreadsheet

Tested by usTests this task · Our own test. Five sales sheets and six questions a manager would ask about each, every one with a single right answer. · Higher is better

Claude Opus 5.5, Claude Sonnet 5, Gemini 3.8 Flash and GPT-6 Sol are level at the top.

Claude Opus 5.5 · Anthropic30/30
Claude Sonnet 5 · Anthropic30/30
Gemini 3.8 Flash · Google DeepMind30/30
GPT-6 Sol · OpenAI30/30
DeepSeek V4 Pro · DeepSeek29/30
GPT-6 Luna · OpenAI26/30
Source: Normie Mode, tested by us · run 24 Sept 2026 · see every answer

Pulling information out of documents into tables

Tests a related skill · Reading documents and filling in a table with the right figures, including cases that need reasoning. · Higher is better

Claude Fable 5.1 leads, followed by GPT-6 Astra and Gemini 3.1 Pro.

Claude Fable 5.1 · Anthropic98%
GPT-6 Astra · OpenAI97%
Gemini 3.1 Pro · Google DeepMind97%
GPT-5.6 Sol · OpenAI96%
Gemini 3.8 Flash · Google DeepMind96%
Gemini 3.6 Flash · Google DeepMind95%
DeepSeek V4 Pro · DeepSeek94%
Claude Sonnet 5 · Anthropic92%
Kimi K3 · Moonshot AI91%
DeepSeek V4.1 Flash · DeepSeek90%
GPT-5.6 Luna · OpenAI89%
Gemini 3.5 Flash-Lite · Google DeepMind83%
Claude Haiku 4.5 · Anthropic74%
Source: DTBench authors via Epoch AI · CC BY 4.0

Professional tasks in banking, consulting and law

Tests a related skill · Tasks written by experienced professionals that take a person about two hours, using documents, spreadsheets, email and slides. · Higher is better

Claude Fable 5.1 leads, followed by GPT-6 Astra and Gemini 3.8 Flash.

Claude Fable 5.1 · Anthropic69%
GPT-6 Astra · OpenAI65%
Gemini 3.8 Flash · Google DeepMind64%
Claude Sonnet 5 · Anthropic55%
Kimi K3 · Moonshot AI51%
DeepSeek V4 Pro · DeepSeek47%
Gemini 3.6 Flash · Google DeepMind47%
Gemini 3.1 Pro · Google DeepMind35%
Source: Mercor via Epoch AI · CC BY 4.0

People's votes on business and finance questions

General ability · People compared two anonymous answers to business, management and finance questions. · Higher is better

Claude Opus 5.5 and Claude Fable 5.1 are neck and neck at the top, followed by Gemini 3.8 Flash and Kimi K3; Claude Fable 5.1 costs about 3 times as much.

Claude Opus 5.5 · Anthropic1st
Claude Fable 5.1 · Anthropic2nd
Gemini 3.8 Flash · Google DeepMind3rd
Kimi K3 · Moonshot AI4th
Gemini 3.6 Flash · Google DeepMind5th
DeepSeek V4.1 Flash · DeepSeek6th
Gemini 3.1 Pro · Google DeepMind7th
GPT-5.6 Sol · OpenAI8th
GPT-6 Astra · OpenAI9th
DeepSeek V4 Pro · DeepSeek10th
GPT-5.6 Luna · OpenAI11th
Claude Sonnet 5 · Anthropic12th
Gemini 3.5 Flash-Lite · Google DeepMind13th
Claude Haiku 4.5 · Anthropic14th
Source: LMArena · votes as of 25 Sept 2026

If you build with it

What the makers charge developers who use the models directly. Using an app? The plans above are what you pay.

Cost per 1,000 typical requests

List price, about 1,500 words in and 500 out per request · Lower is better

GPT-6 Luna is cheapest, followed by DeepSeek V4.1 Flash and GPT-5.6 Luna.

GPT-6 Luna · OpenAI$0.55
DeepSeek V4.1 Flash · DeepSeek$0.72
GPT-5.6 Luna · OpenAI$1.24
DeepSeek V4 Pro · DeepSeek$1.48
Gemini 3.5 Flash-Lite · Google DeepMind$2.35
Gemini 3.8 Flash · Google DeepMind$4.13
Gemini 3.6 Flash · Google DeepMind$4.13
Claude Haiku 4.5 · Anthropic$5.50
Claude Sonnet 5 · Anthropic$11
GPT-6 Sol · OpenAI$11
Gemini 3.1 Pro · Google DeepMind$12
Kimi K3 · Moonshot AI$17
GPT-5.6 Sol · OpenAI$22
Claude Opus 5.5 · Anthropic$22
GPT-6 Astra · OpenAI$55
Claude Fable 5.1 · Anthropic$55
Source: models.dev · MIT

More specific tasks

Intelligence Snacks newsletter

The big AI ideas each week, in your inbox