Guide

Pick the right model without leaderboards

Default to Ashna-X1. Pin GPT, Claude, or Gemini only when you need a catalog flag such as context or reasoning. Leaderboard rank is not a routing rule.

AshnaAI

Pick the right model without leaderboards

What you'll do

Default to Ashna-X1. Pin GPT, Claude, or Gemini only when you need a catalog flag such as context or reasoning. Leaderboard rank is not a routing rule.

This guide walks through how to choose an LLM in AshnaAI. You stay in chat. You do not need a separate desktop of buttons for each file job.

Before you start

Open AshnaAI and start a new chat.

How to how to choose an LLM

Follow the steps below in order. Confirm in chat before AshnaAI sends, posts, or writes to Tally.

Step 1. Read the definition

Default to Ashna-X1. Pin GPT, Claude, or Gemini only when you need a catalog flag such as context or reasoning. Leaderboard rank is not a routing rule.

Step 2. Open AshnaAI

Sign in at https://app.ashna.ai and start a chat, or open the agent builder.

Step 3. Try the job

Leave X1 on, then pin a model only if a catalog row requires it.

Step 4. What to expect

Documents still use the file path. X1 does not replace chat-with-file.

Keep in mind

Documents still use the file path. X1 does not replace chat-with-file.

Related guides

Also read use ashna x1 instead of picking models yourself.

Also read llm routing match tasks to models.

More AI glossary how-tos live on What is RAG, hallucination, and prompt engineering.

Try it now

Open app.ashna.ai and run this job in a new chat. New accounts can start from app.ashna.ai/signup.

Frequently asked questions

What is how to choose an LLM?
Default to Ashna-X1. Pin GPT, Claude, or Gemini only when you need a catalog flag such as context or reasoning. Leaderboard rank is not a routing rule.
How does AshnaAI use this?
X1 is the default router.
Do I need to train a model?
Usually no. Prefer files, connectors, and a clear job over fine-tuning.
Where is the glossary entry?
Read https://www.ashna.ai/ai-glossary/benchmark
What should I do next?
Leave X1 on, then pin a model only if a catalog row requires it.

Tags

#AI glossary#how to choose an LLM#how-to

Found this article helpful? Share it with your network.