Benchmark Almanac

GJ.cool Vertical Book OCR Evaluation

PaddleOCR-VL-1.5 97.4% tops its leaderboard GLM-OCR 89% leads the models we track
Not in model cards

Models transcribe vertically printed Chinese books and manuscripts. The authors report accuracy separately for pages with sparse interlinear notes, pages with dense notes, and manuscripts.

GJ.cool publishes vertical accuracy for seven models. Six have breakdowns by page type. Qwen3.5 thinking mode timed out on 38 percent of pages.

Released
April 2026
Kind
Documents, charts and text in images
Level
University
Scored
Checked automatically
Answers
Open-ended
Measures
Capability
Language
Chinese
In and out
Documents → Text
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
A host
Last model added
February 2026
Scores refreshed
November 20th, 2026
7
Entries on its own leaderboard, 2 models we track

PaddleOCR-VL-1.5 tops the leaderboard with 97.4% GLM-OCR leads with 89%

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is GLM-OCR, at 89%. This view shows only models we track, each at its best.

  1. 1 PaddleOCR-VL-1.5 97.4%
  2. 2 chandra-ocr-2 92.6%
  3. 3 dots.ocr 91.9%
  4. 4 chandra 91.1%
  5. 5 GLM-OCR 89%
  6. 6 Qwen3.5-4B no think 81.9%
  7. 7 dots.mocr 69.2%

Source: Official GJ.cool Vertical Book OCR Evaluation leaderboard

Source: Official GJ.cool Vertical Book OCR Evaluation leaderboard

#EntryScoreSettingDateSource
1 PaddleOCR-VL-1.5 0.9B 97.4% Official leaderboard
2 chandra-ocr-2 4B 92.6% Official leaderboard
3 dots.ocr 3B 91.9% Official leaderboard
4 chandra 9B 91.1% Official leaderboard
5 GLM-OCR 89% Jan 2026 Official leaderboard
6 Qwen3.5-4B 81.9% no think Feb 2026 Official leaderboard
7 dots.mocr 3B 69.2% Official leaderboard
#ModelScoreSettingDateSource
1 GLM-OCR 89% Jan 2026 Official leaderboard
2 Qwen3.5-4B 81.9% no think Feb 2026 Official leaderboard

GLM-OCR on the official leaderboard passed 85% in January 2026

Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) GLM-OCR 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) GLM-OCR

Source: Official GJ.cool Vertical Book OCR Evaluation leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Vision

All 636 in Vision
  • MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy. Qwen 3.6 Plus 86%
  • MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. GPT-5.6 Sol 84.6%
  • CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
  • MathVista In use Math reasoning in visual contexts (charts, geometry, puzzles) from 31 datasets. Answer accuracy. Seed2.1 Pro 90.7%
  • MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy. Qwen 3.8 Max 97.7%
  • MMStar In use Models answer 1,500 human-curated image questions that cannot be solved without the image, across 6 core capabilities. Scored by accuracy. Qwen 3.8 Max 85.9%

Data audit

7 of 8 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark

Catalog record 1 warning 1 pass
  • Warning Task access We don’t know whether the tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (7 entries).
  • Pass Models scored 2 models we track, plus 5 other entries on its leaderboard.
  • Note Newest score The newest came 9 months ago, in February 2026, for Qwen3.5-4B. That’s expected for a saturated test.
  • Note Frontier models None of its models are on the capabilities index.
  • Note Headroom Saturated. The best is 89%, past 85% since January 2026.
Leaderboard import 3 pass
  • Pass Importer We read the board on ocr.gj.cool: 2 rows for models we track and 5 other entries at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check