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

Best AI for legal questions

Understanding contracts, regulations and legal questions.

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 less

Gemini 3.8 Flash

Get it with Google AI Pro, $19.99 a month

2nd of 8 models for this task

Best free

Kimi K3

Get it with Kimi Free

4th of 8 models for this task

Keep in mind Mostly based on people's votes.

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.
3rd of 8
ChatGPT Pro$100 a monthGPT-6 Astra
Called GPT-6 Pro in the app
3rd of 8
Claude FreefreeClaude Sonnet 55th of 8
Claude Pro$20 a monthClaude Sonnet 5
Its main model, Claude Opus 5.5, is too new to score yet.
5th 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 Flash2nd of 8
Google AI Ultra$99.99 a monthGemini 3.8 Flash2nd of 8
Kimi FreefreeKimi K34th of 8
Kimi Moderato$19 a monthKimi K34th of 8

Norm's guide

What I'd tell a friend who asked.

What AI is good at

  • Explaining what a contract clause means in plain English.
  • Spotting parts of a document worth asking about.
  • Drafting a first version of a simple letter.

Where it trips up

  • Laws differ by country and change over time.
  • Inventing cases or rules that sound real.
  • Missing what matters in your particular situation.

How to get a good result

  • Tell it which country you're in.
  • Ask it what questions to put to a lawyer.
  • Have anything important checked by a qualified person.

How the models compare

Every model we could score for legal questions, combining the tests below.

Overall for legal questions

Position on a combined score from 2 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 Gemini 3.8 Flash and GPT-6 Astra.

Claude Fable 5.1 · Anthropic1st
Gemini 3.8 Flash · Google DeepMind2nd
GPT-6 Astra · OpenAI3rd
Kimi K3 · Moonshot AI4th
Claude Sonnet 5 · Anthropic5th
Gemini 3.6 Flash · Google DeepMind6th
DeepSeek V4 Pro · DeepSeek7th
Gemini 3.1 Pro · Google DeepMind8th

The evidence

People's votes on legal questions

Tests this task · People compared two anonymous answers to legal and government questions. · Higher is better

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

Claude Fable 5.1 · Anthropic1st
Claude Opus 5.5 · Anthropic2nd
Kimi K3 · Moonshot AI3rd
Gemini 3.8 Flash · Google DeepMind4th
Gemini 3.1 Pro · Google DeepMind5th
Gemini 3.6 Flash · Google DeepMind6th
GPT-5.6 Sol · OpenAI7th
DeepSeek V4 Pro · DeepSeek8th
GPT-6 Astra · OpenAI9th
Claude Sonnet 5 · Anthropic10th
GPT-5.6 Luna · OpenAI11th
DeepSeek V4.1 Flash · DeepSeek12th
Gemini 3.5 Flash-Lite · Google DeepMind13th
Claude Haiku 4.5 · Anthropic14th
Source: LMArena · votes as of 25 Sept 2026

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

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
Intelligence Snacks newsletter

The big AI ideas each week, in your inbox