> ## Documentation Index
> Fetch the complete documentation index at: https://docs.viorant.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Compare variants

> Try it three ways — run variants side by side on the same input.

**Evals** answer a question you otherwise answer by guessing: *is this version actually
better than that one?*

Pick a prompt, skill or agent, pin up to three variants of it, run them all on the same
input, and read the results next to each other.

## Opening evals

The top bar carries an **Editor / Evaluation** toggle. Switching to **Evaluation** opens
a drawer beneath the editor area. It follows whatever you're looking at, so switching tabs
re-targets the eval.

## Setting one up

<Steps>
  <Step title="Pick a target type">
    **Prompt**, **Skill** or **Agent** — one type per eval. You compare a thing against
    itself, not a prompt against an agent.
  </Step>

  <Step title="Add variants">
    Each variant is a **version** and a **model**. Up to three. Any model active in the
    Space is available.
  </Step>

  <Step title="Fill in the input">
    Prompt variables come from the prompt's own values. A required variable left blank is
    an error rather than an empty run.
  </Step>

  <Step title="Run">
    All variants run in parallel against the same input.
  </Step>
</Steps>

## Reading the results

Outputs sit side by side, with tokens and cost per variant.

**They're shown as outputs, not as a diff.** Diffing three model outputs is noise — nearly
every token differs even when the substance is identical. Read them; the interesting
differences are rarely textual.

A variant that fails doesn't take the others down. It reports its own error and the rest
keep going.

## Cost

Before running, you see an estimate. Three variants means three real runs charged the
normal way, so a three-variant eval costs roughly three times a single run.

<Note>
  Skill versions can't be pinned. Skills are filesystem-canonical — the file on disk is the
  skill — so there's no version history to select from. Compare skills across models
  instead.
</Note>

## History

Every eval is kept and can be reopened. Results are written as files in the Space, so they
travel with it and can be committed like anything else. Delete one when you don't need it.

<Card title="Run an agent locally" icon="play" href="/run-agent-locally">
  Single runs, for when you're not comparing.
</Card>