Benchmark Almanac

olmOCR-Bench

OXR-1.0 87.8% leads since October 2026
DeepSeek-OCR 75.7% leads
OXR-1.0 87.8% leads since October 2026
In use

The official leaderboard hasn’t scored a model released after DeepSeek-OCR (October 2025). Labs report their own numbers for one newer model: MiniCPM-OCR-1.0 at 82.7%.

OCR systems convert 1,403 PDFs to markdown. 7,010 unit tests check text presence and absence, reading order, tables and math.

On Hugging Face's official benchmark list. Many OCR model cards report it.

Released
February 2025
Kind
Documents, charts and text in images
Level
Everyday
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Documents → Text, Tables
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
Last in a launch post
October 2026
Last model added
October 2026
Scores refreshed
November 20th, 2026
3
Models scored in lab cards
3
Launch posts list it, from 3 labs

OXR-1.0 leads with 87.8%

Best score per model as labs report them in their own cards, drawn striped. Labs pick their own settings, so these compare less cleanly than independent runs.

DeepSeek-OCR leads with 75.7% across all independent runs

Best score per model across the official leaderboard, Epoch AI’s own runs and any board Epoch AI copied. Dotted bars are reruns by Epoch AI or another board, and each row names its source.

OXR-1.0 leads with 87.8%, claims included

Best score per model from every source, including labs’ own numbers and claims Epoch AI collected from reports and papers. Labs pick their own settings, so a claim can beat an independent run of the same model. Striped bars are claims, and dotted bars are reruns by Epoch AI or another board.

  1. 1 OXR-1.0 87.8%
  2. 2 Surya OCR 2.5 83.7%
  3. 3 MiniCPM-OCR-1.0 82.7%

Source: Labs’ model cards

Source: Official olmOCR-Bench leaderboard

Sources: Labs’ model cards and official olmOCR-Bench leaderboard

#ModelScoreSettingDateSource
1 OXR-1.0 87.8% Oct 2026 Lab model card
2 Surya OCR 2.5 83.7% Oct 2026 Lab model card
3 MiniCPM-OCR-1.0 82.7% Oct 2026 Lab model card
#ModelScoreSettingDateSource
1 DeepSeek-OCR 75.7% Oct 2025 Official leaderboard
#ModelScoreSettingDateSource
1 OXR-1.0 87.8% Oct 2026 Lab model card
2 Surya OCR 2.5 83.7% Oct 2026 Lab model card
3 MiniCPM-OCR-1.0 82.7% Oct 2026 Lab model card
4 DeepSeek-OCR 75.7% Oct 2025 Official leaderboard

The benchmark's own leaderboard has 9 entries, 1 of them models we track. Switch the scores above to rank them together.

Number one over time Number one over time 2 models have held number one with claims included since its release in February 2025

Lab claims count from the day the card came out, independent runs from the model’s release.

SoMark
Lab claims Passed 85% in Oct 2026, by OXR-1.0
OXR-1.0 87.8%

Source: Labs’ model cards

SoMark’s own number for OXR-1.0 passed 85% in October 2026

That was 20 months after its release. By the same age, 26% of the benchmarks from 2025 had passed 85%. All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard Reported by the lab in its model card Best so far
0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) OXR-1.0 DeepSeek-OCR 0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) OXR-1.0 DeepSeek-OCR

Sources: Official olmOCR-Bench leaderboard and labs’ model cards

3 labs put it in a launch post in the last six months

Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.

SoMark
Datalab
OpenBMB (ModelBest)
DateLaunch postScoreAs the post writes it
Oct 28, 2026 MiniCPM-OCR-1.0 82.7 olmOCR-bench
Oct 25, 2026 Surya OCR 2.5 83.7 83.7% on olmOCR-bench
Oct 5, 2026 OXR-1.0 87.8 olmOCR-bench Overall

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

All 9 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (9 entries) and launch posts (3 scores).
  • Pass Models scored 4 models we track, plus 8 other entries on its leaderboard.
  • Pass Newest score The newest is from October 2026, for MiniCPM-OCR-1.0.
  • Note Frontier models None of its models are on the capabilities index.
  • Note Headroom Saturated. The best is 87.8%, past 85% since October 2026.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 1 row for models we track and 8 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