Best AI for building apps

Making phone and desktop apps, from idea to working version.

Best overallToo close to call

Claude Fable 5.1Get it with Claude Max, $100 a month (for up to half your weekly allowance)
GPT-6 AstraGet it with ChatGPT Plus, $20 a month (only in ChatGPT's Work mode and Codex, not normal chat)

1st and 2nd of 10 models for this task

Best for $25 a month or less

GPT-6 Astra

Get it with ChatGPT Plus, $20 a month (only in ChatGPT's Work mode and Codex, not normal chat)

2nd of 10 models for this task

Best free

Kimi K3

Get it with Kimi Free

4th of 10 models for this task

Based on the tests for coding and building apps. 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 plan	Price	Best model on it for this	Position
ChatGPT Free	free	GPT-5.6 Luna	7th of 10
ChatGPT Go	$8 a month	GPT-5.6 Luna	7th of 10
ChatGPT Plus	$20 a month	GPT-6 Astra Only in ChatGPT's Work mode and Codex, not normal chat	2nd of 10
ChatGPT Pro	$100 a month	GPT-6 Astra Called GPT-6 Pro in the app	2nd of 10
Claude Free	free	Claude Sonnet 5	6th of 10
Claude Pro	$20 a month	Claude Sonnet 5 Its main model, Claude Opus 5.5, is too new to score yet.	6th of 10
Claude Max	$100 a month	Claude 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 10
Gemini Free	free	Gemini 3.6 Flash	8th of 10
Google AI Plus	$4.99 a month	Gemini 3.6 Flash	8th of 10
Google AI Pro	$19.99 a month	Gemini 3.8 Flash	5th of 10
Google AI Ultra	$99.99 a month	Gemini 3.8 Flash	5th of 10
Kimi Free	free	Kimi K3	4th of 10
Kimi Moderato	$19 a month	Kimi K3	4th of 10

How the models compare

Every model we could score for building apps, combining the tests below.

Overall for building apps

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 GPT-5.6 Sol.

Claude Fable 5.1 · Anthropic1st

GPT-6 Astra · OpenAI2nd

GPT-5.6 Sol · OpenAI3rd

Kimi K3 · Moonshot AI4th

Gemini 3.8 Flash · Google DeepMind5th

Claude Sonnet 5 · Anthropic6th

GPT-5.6 Luna · OpenAI7th

Gemini 3.6 Flash · Google DeepMind8th

Gemini 3.1 Pro · Google DeepMind9th

DeepSeek V4 Pro · DeepSeek10th

The evidence

Would a real maintainer accept its code?

Tests a related skill · Coding tasks in 36 major open-source projects, judged on whether the code is good enough to merge, not just whether it runs. · Higher is better

GPT-6 Astra leads, followed by Claude Fable 5.1 and GPT-5.6 Sol.

GPT-6 Astra · OpenAI53%

Claude Fable 5.1 · Anthropic51%

GPT-5.6 Sol · OpenAI47%

Kimi K3 · Moonshot AI44%

Claude Sonnet 5 · Anthropic43%

Gemini 3.8 Flash · Google DeepMind41%

GPT-5.6 Luna · OpenAI40%

Gemini 3.6 Flash · Google DeepMind34%

DeepSeek V4 Pro · DeepSeek29%

Source: Cognition via Epoch AI · CC BY 4.0

Building features in real software projects

Tests a related skill · 113 original tasks across 91 real code projects in five languages, checked with hand-written tests. · Higher is better

GPT-6 Astra leads, followed by Gemini 3.8 Flash and GPT-5.6 Sol.

GPT-6 Astra · OpenAI74%

Gemini 3.8 Flash · Google DeepMind74%

GPT-5.6 Sol · OpenAI73%

Kimi K3 · Moonshot AI69%

GPT-5.6 Luna · OpenAI67%

Claude Sonnet 5 · Anthropic54%

Gemini 3.6 Flash · Google DeepMind47%

Gemini 3.1 Pro · Google DeepMind12%

Source: Datacurve via Epoch AI · CC BY 4.0

People's votes on coding questions

Tests a related skill · People compared two anonymous answers to their coding questions and picked the better one. · 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 DeepSeek V4.1 Flash; 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

DeepSeek V4.1 Flash · DeepSeek4th

Kimi K3 · Moonshot AI5th

GPT-5.6 Sol · OpenAI6th

Gemini 3.6 Flash · Google DeepMind7th

GPT-6 Astra · OpenAI8th

Claude Sonnet 5 · Anthropic9th

Gemini 3.1 Pro · Google DeepMind10th

DeepSeek V4 Pro · DeepSeek11th

GPT-5.6 Luna · OpenAI12th

Gemini 3.5 Flash-Lite · Google DeepMind13th

Claude Haiku 4.5 · Anthropic14th

Source: LMArena · votes as of 25 Sept 2026

Also relevant, but too few of our models tested to compare yet: Getting jobs done on a computer's command line (2 models).

Also relevant, but no results for the models we compare yet: Fixing reported bugs in real software.

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