How well does export hold the pixels?
PPTX exports rendered as images and diffed against Gamma's own render — a frozen benchmark for the comparable accuracy number, rolling sweeps for what exists right now, and the corpus itself, deck by deck, card by card.
each number is visual fidelity, 100 − mean changed pixels per slide, from that series' latest run · Δ compares the previous run of the same series
Export fidelity over time
The canonical export accuracy number: visual fidelity of the PPTX exporter over the frozen, versioned export-decks benchmark — exported decks rendered as images and diffed against Gamma's own render, measured weekly.
Run statistics, week by week
The distribution behind each weekly headline: per-cohort mean, median, p90, p95, and worst-slide changedPct. The tail percentiles show whether a score moved because everything shifted or because a few slides broke.
pdf export · poppler render
| cohort | scope | n | fidelity | mean changed | p50 changed | p90 changed | p95 changed | worst changed | Δ mean |
|---|---|---|---|---|---|---|---|---|---|
| overall | per slide | 606 | 98.31% | 1.69% | 1.02% | 2.75% | 4.57% | 47.97% | — |
| per deck | 39 | — | 1.61% | 1.32% | 2.91% | 4.33% | 4.68% | -0.08pp | |
| templates | per slide | 439 | 98.28% | 1.72% | 0.96% | 2.5% | 5.22% | 47.97% | — |
| per deck | 19 | — | 1.74% | 1.32% | 2.71% | 4.56% | 4.68% | +0.02pp | |
| imports | per slide | 63 | 99% | 1% | 0.89% | 1.6% | 2.03% | 4.44% | — |
| per deck | 10 | — | 1.1% | 0.92% | 1.61% | 2.23% | 2.86% | +0.1pp | |
| remixes | per slide | 104 | 98.01% | 1.99% | 1.35% | 4.05% | 4.94% | 15.41% | — |
| per deck | 10 | — | 1.87% | 1.75% | 3.23% | 3.77% | 4.31% | -0.12pp |
Per-slide rows pool every slide's changedPct in the cohort, so large decks weigh more. Per-deck rows take each deck's mean changedPct first, so every deck weighs the same. Δ mean is per-deck mean minus per-slide mean in percentage points: positive means small decks export worse than the pooled score suggests, negative means large decks do. Worst is the single most-changed slide (or deck). Runs before percentile capture show —. Runs that cover extra export formats get one table per format.
Rolling export sweeps
Export fidelity of what exists right now — the current official template catalog (Tue/Thu, full corpus) and freshly sampled staging gammas (twice daily), plotted as 100 − mean changedPct per run. The corpus shifts as templates and gammas change, so these lines show coverage and discovery; the frozen benchmark above is the comparable accuracy number.
Structural fidelity
What survives export as native OOXML, independent of pixels: chart and table survival, image drops, autofit health, and typed shape-level deltas from the struct-diff suites — ideal-GML → export over grid-templates, and the full PPTX round trip (source → import → export) with per-leg loss attribution.
What the benchmark covers
The frozen corpus roster: cohort sizes, card counts, locales, scripts, and themes, with each deck's provenance. The roster changes only at deliberate benchmark version bumps, so scores stay comparable within a version.
The corpus, deck by deck
Every deck in the frozen benchmark, sorted worst-first from the latest baseline run. Open a deck to compare each card three ways: Gamma's own render (truth), the render of the PPTX export, and the pixel-diff heatmap between them.
Factory runs
Triage-and-fix sweeps over the ticket queues — export, templates, frontier, and import — with what each run fixed, routed to a human, or skipped as already claimed, plus the draft PRs it produced.
| date | area | run | fixed | routed | bounced | skipped | PRs |
|---|---|---|---|---|---|---|---|
| 2026-09-04 | export | pptx-export fix loop: EDI-12269 painted custom-mask accents | 1 (EDI-12269) | 0 | 0 | 0 | gamma#35172 |
| 2026-08-31 | import | import-fidelity backlog triage + fix | 1 (EDI-11392) | 2 | 0 | 4 | gamma#34099 · import-decks-dataset#2202 |
| 2026-08-31 | frontier | expressiveness-factory queue run | 1 (EDI-7976) | 6 | 1 | 6 | gamma#34097 |
| 2026-08-31 | templates | template-library triage + fix sweep | 1 (EDI-11340) | 1 | 0 | 21 | gamma#34096 · template-library#289 |
Fixed = tickets that produced a draft PR with evidence. Routed = tickets handed to a human with a diagnosis comment (product/design decisions, unsafe or blocked repros). Bounced = tickets returned for missing information. Skipped = tickets left untouched because another session, assignee, or open PR already had them.