chrome-nano-extract-bench

Structured extraction from screenshots with Chrome's built-in on-device model. Three input paths over the same fixtures and the same schema: vision (image → model), ocr (image → Tesseract.js → text → model), hybrid (ocr as the base, vision only for price, skipped when no quote panel is detected). Everything runs locally in this tab. Serve the repo over HTTP (python -m http.server) so fixtures/out/labels.json can be fetched; file:// blocks it.

checking model… checking OCR… loading fixtures…

Run

paths:
rules (prompt variants, each run separately):
hybrid options: order: sampling: vision: OCR preprocess:
fixture filter:

Summary

Counts are over successful (parsed) runs. distractor→change is the number of runs where change_percent equals the body's inflation/rate percentage — the contamination this benchmark exists to measure. copied is the headline being the page's deck line verbatim (only possible on deck fixtures).

By variable (path × rules, split by lang / panel / deck)

Fixtures

OCR text

none yet

Log

#fixturepathrulesrunheadlinetopiclangcopiedchangepricedateinstrsentmsstatus