Skip to main content
Simulation shows how the target did. Before/after shows how it did compared to the baseline. The number that matters.

The comparison view

For every dataset example:
  • Left: baseline output.
  • Center: target output.
  • Right: expected output.
  • Verdict: improvement / regression / same / both failed.
Sort by verdict:
  • Improvements first — where the target beat the baseline.
  • Regressions first — where the target broke something the baseline handled.
  • Diff score — biggest change in either direction.

Summary metrics

At the top:
  • Pass rate delta — target’s pass rate minus baseline’s.
  • Improvements — count of “target beat baseline”.
  • Regressions — count of “target worse than baseline”.
  • Wash — count of “same verdict”.
  • Cost delta — is the target more or less expensive?
  • Latency delta — is the target slower or faster?
Big improvement, small regression, minor cost increase → likely ship it. Big regression → don’t.

The regression drill-down

Regressions are the deal-breakers. Click View regressions to see just those examples. For each regression:
  • What the baseline said.
  • What the target now says (worse).
  • Why it changed — Nora’s automated diff of the trace shows what step diverged.
Common causes:
  • New prompt is more terse and drops a required disclaimer.
  • New retrieval preset drops a source the baseline relied on.
  • Model swap changes an edge behavior.

The improvement drill-down

Similar view for improvements. Understand why the target won so you can generalize:
  • Was it a specific pattern that the change targeted?
  • Or did it broadly lift many examples?
Broad improvements are safer to ship than narrow ones.

Statistical significance

For datasets with < 50 examples, Nora shows a “high variance — proceed with caution” flag. Small samples make it easy to see noise as signal. For > 50 examples, a proper significance test is shown: p-value for pass-rate delta, confidence interval. Only trust deltas outside the noise floor.

Attributed changes

The improvement flow tags every simulation with the specific proposal that generated the target. Before/after inherits that tag, so you can trace:
“Improvement #42 (retrieval preset change): +8% pass rate, +1 regression, +0.02s latency”
Great for building an audit trail of what changed and why.

Multi-target comparison

Compare more than two versions at once. Add up to 5 targets to a comparison — the view expands to columns. Useful for comparing three model choices, or three prompt variants, side-by-side.

Sharing a comparison

Every simulation comparison has a permalink. Share with reviewers before shipping. They see the same view — no data extraction needed. Approvers can approve the change directly from the comparison view (see Approve).