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

# Review

> Overlay several runs and decide which one to keep.

Pick two or more jobs and the console overlays their curves, diffs their configs, and shows a
scorecard. The question it is built to answer is not "what happened" but "did this get better, and
which run do we keep".

<Frame caption="Review: overlaid curves, a scorecard, and the config diff explaining why they differ.">
  <img src="https://mintcdn.com/starforge/GatXR2rI5-_Vm4_H/images/console/review.png?fit=max&auto=format&n=GatXR2rI5-_Vm4_H&q=85&s=c0f89b6e81c660ea39a15053b551c9a9" alt="StarForge review page" width="2160" height="1350" data-path="images/console/review.png" />
</Frame>

## What you see

| Region             | What it shows                                                                              |
| ------------------ | ------------------------------------------------------------------------------------------ |
| **Scorecard**      | Benchmark scores side by side, with regressions marked by each metric's declared direction |
| **Primary curves** | Validation accuracy and training reward, overlaid                                          |
| **Config diff**    | Only the keys that actually differ, so a fifty-key config reduces to the three you changed |
| **Ask Agent**      | Ask in plain language whether the runs improved and which to keep                          |

The config diff is the part people underuse. Two runs that disagree on a curve almost always
disagree on a config key, and the diff finds it faster than reading two YAML files.

## What you can do

* **Add or remove runs** — the overlay updates without reloading.
* **Ask Agent** — natural-language analysis of the selected runs. Locked to administrators unless
  the deployment sets `FORGE_PREMIUM_PUBLIC`.
* **Share** — a read-only link to this exact comparison, with an expiry. See
  [sharing](/en/console/sharing).

## Reading a comparison honestly

<AccordionGroup>
  <Accordion title="Identical configs, different curves" icon="dices">
    Seeds. Post-training runs vary between identical configurations, sometimes considerably. Two runs
    is not a result; if the difference matters, run the variant again.
  </Accordion>

  <Accordion title="Better on the primary metric, worse elsewhere" icon="scale">
    The normal outcome, and the reason the scorecard shows several benchmarks rather than one. Post-
    training reliably improves one axis while quietly damaging another — that is what the math, code,
    knowledge, Chinese and instruction-following split exists to make visible.
  </Accordion>

  <Accordion title="Reward climbing, benchmark flat" icon="trending-up">
    The model is getting better at your reward, not at the task. Worth looking at the validation
    samples before celebrating: reward hacking looks exactly like this from the curve alone.
  </Accordion>
</AccordionGroup>