Best AI for writing a Python script right now

Updated Oct 24, 2026. Checked daily.

Say the input, the output, and one example. Ask for a script you can run, plus how to run it.

The coding board measures coding work. It does not run the script on your machine.

Try this prompt

Write a Python script that does this job. Include a short example of how to run it.

Do not include secrets or private files in the prompt if the chat trains on chats by default.

#1 Champion

Anthropic

Claude app, Pro plan ($20/month), choose Opus 5.5.

Paid plan

3 of 4 sources agree

Tops major coding benchmarks and leads LMArena for building software and complex debugging.

LMArena Code 1813; #1 SWE-bench Pro (89.9%)

Details

Why it leads: LMArena Code 1813; #1 SWE-bench Pro (89.9%) Source.
Cost: Pro is $20/month ($17/month billed annually); API is $4 per million input tokens and $20 per million output tokens.
Free tier: Not on the free plan. Free Claude includes Haiku and Sonnet, not Opus.
Privacy default: Anthropic says Free, Pro, and Max chats are used for training only if you allow it, and you choose at signup. The toggle has been reported as on by default, so check it. Settings, then Privacy. Turn off Help improve Claude. Source
When not to use it: Skip it for simple edits and quick boilerplate where faster, cheaper models suffice.
Starter prompt: Find the bug in this function, explain the cause, and give the fixed version.

Top Alternative

OpenAI

ChatGPT Plus ($20/month), then select GPT-6 Astra in Work or Codex.

Paid plan

Ranks near the frontier on SWE-bench and LMArena while integrating directly with OpenAI's Codex tooling.

LMArena Code 1786.1; 90.2% on SWE-bench Pro V2 HARD

Details

Why it leads: LMArena Code 1786.1; 90.2% on SWE-bench Pro V2 HARD Source.
Cost: Plus is $20/month; API is $10 per million input tokens and $50 per million output tokens.
Free tier: Not on the free plan. Plus includes access inside Work and Codex.
Privacy default: Yes on personal Free, Plus, and Pro. Improve the model for everyone is on by default. Settings, Data controls, turn off Improve the model for everyone. Source
When not to use it: Skip it if you want to run completely offline without sending source code to proprietary servers.
Starter prompt: Implement this feature in the repo, then list the files you changed and why.

Best Open Source

Moonshot AI

Download weights on Hugging Face, or select Kimi K3 in the Kimi web app.

Free (limited)

A massive open-weight model delivering near-frontier coding performance that you can self-host for total privacy.

LMArena Code not cited; 88.2% on SWE-bench Pro V2 HARD.

Details

Why it leads: LMArena Code not cited; 88.2% on SWE-bench Pro V2 HARD. Source.
Cost: Free to download weights; hosted Kimi app is free with usage limits or available via API.
Free tier: Yes, available for free with standard rate limits in the Kimi web and mobile apps.
Privacy default: Yes. The Kimi consumer policy says prompts and files can be used to improve models. Ask Kimi support to stop training use if the app has no toggle. Source
When not to use it: Skip self-hosting if you lack multi-GPU cluster infrastructure required to serve 2.8 trillion parameters.
Starter prompt: Refactor this module for clarity and add tests for the edge cases.