BENCHMARKS Chandra leads open-source OCR. The Datalab API ships a tuned variant. ← All benchmarks
MATH · OLMOCR-BENCH · OLD SCANS MATH

Math — 90.2% on olmOCR-bench · Old Scans Math.

Old Scans Math measures OCR on equations from scanned mathematical texts — typeset, handwritten, and mixed. Math in non-Latin scripts is especially hard; we score it directly.

SCOREBOARD · olmOCR-bench · Old Scans Math

Ranked scoreboard.

Models ranked highest-to-lowest. Datalab variants in accent; competitors and prior generations in muted ink.

Rank Model Score vs scale
01 Datalab API 90.2%
02 Chandra 2 OSS 89.3%
03 Chandra 1 prior generation 80.3%
Dataset · olmOCR-bench · Old Scans Math Last run · 2026-03-18

+9.0 vs prior generation

WHY THIS NUMBER IS CREDIBLE

olmOCR-bench unit-tests OCR output against known-correct elements in a public dataset. Model versions pinned per run; anyone can reproduce from the olmOCR-bench HuggingFace dataset.

START

Printed, handwritten, mixed-script equations.

Run a math PDF on Chandra — free tier, no credit card.