OmniParseBench
Document parsers convert single pages to text, and 16,288 binary unit tests on 2,937 pages check the output. The headline joins text, table and layout subscores.
The results table also lists cost per 1,000 pages and refusals. Code is Apache 2.0 and page data keeps each source's license. Datalab includes its own parsers.
- Made by
- Datalab
- Released
- October 2026
- Kind
- Documents, charts and text in images
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
-
Gemini 4 Carbon #3 on the capability index
- Last in a launch post
- October 2026
- Last model added
- October 2026
- Scores refreshed
- November 20th, 2026
Gemini 4 Argon leads with 96.0 Gemini 4 Argon leads with 96.0
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. This view shows only models we track, each at its best.
Gemini 4 Argon leads with 96.0, 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.
- 96.0
Gemini 4 Argon
- 95.7
Gemini 4 Carbon
- 94.4 Datalab accurate
- 92.9 Datalab balanced
- 92.5
Gemini 3.8 Flash
- 91.5 GPT-6.1 Sol
- 91.1 Reducto
- 90.8 LlamaParse
- 90.4 chandra-ocr-2 (Datalab)
- 90.0 Claude Opus 5.5
- 89.9 Mistral OCR
- 88.9 Claude Sonnet 5.5
- 88.2 dots.mocr
- 87.9 GPT-5.6 Sol
- 87.4 Infinity-Parser2-Pro
- 87.4 MinerU2.5-Pro
- 86.3 Surya OCR 2.5 (Datalab)
- 85.6 OXR-1.0
- 84.5 OvisOCR3
- 83.5
MiniCPM-OCR-1.0
- 83.4 Azure
- 83.4 Extend
- 83.3 Surya OCR 2 (Datalab)
- 83.1 LightOnOCR-3-4B
- 81.9 LightOnOCR-3-0.8B
- 81.9 GLM-OCR
- 81.5
Unlimited OCR 2
- 81.3 PaddleOCR-VL-1.6
- 79.9 Nemotron 3.5 Parse
- 79.5 Unlimited-OCR
- 78.7 Infinity-Parser2-Flash
- 75.4
DeepSeek-OCR 2
- 71.4 Indra OCR (Datalab)
- 68.8 HunyuanOCR-1.5
- 1
Gemini 4 Argon 96.0
- 2
Gemini 4 Carbon 95.7
- 3 Datalab accurate 94.4
- 4 Datalab balanced 92.9
- 5
Gemini 3.8 Flash 92.5
- 6 GPT-6.1 Sol 91.5
- 7 Reducto 91.1
- 8 LlamaParse 90.8
- 9 chandra-ocr-2 (Datalab) 90.4
- 10 Claude Opus 5.5 90.0
- 11 Mistral OCR 89.9
- 12 Claude Sonnet 5.5 88.9
- 13 dots.mocr 88.2
- 14 GPT-5.6 Sol 87.9
- 15 Infinity-Parser2-Pro 87.4
- 16 MinerU2.5-Pro 87.4
- 17 Surya OCR 2.5 (Datalab) 86.3
- 18 OXR-1.0 85.6
- 19 OvisOCR3 84.5
- 20
MiniCPM-OCR-1.0 83.5
- 21 Azure 83.4
- 22 Extend 83.4
- 23 Surya OCR 2 (Datalab) 83.3
- 24 LightOnOCR-3-4B 83.1
- 25 LightOnOCR-3-0.8B 81.9
- 26 GLM-OCR 81.9
- 27
Unlimited OCR 2 81.5
- 28 PaddleOCR-VL-1.6 81.3
- 29 Nemotron 3.5 Parse 79.9
- 30 Unlimited-OCR 79.5
- 31 Infinity-Parser2-Flash 78.7
- 32
DeepSeek-OCR 2 75.4
- 33 Indra OCR (Datalab) 71.4
- 34 HunyuanOCR-1.5 68.8
Source: Official OmniParseBench leaderboard
- 1
Gemini 4 Argon 96.0
- 2
Gemini 4 Carbon 95.7
- 3
Gemini 3.8 Flash 92.5
- 4 GPT-6.1 Sol 91.5
- 5 Claude Opus 5.5 90.0
- 6 Claude Sonnet 5.5 88.9
- 7 GPT-5.6 Sol 87.9
- 8 OXR-1.0 85.6
- 9
MiniCPM-OCR-1.0 83.5
- 10 GLM-OCR 81.9
- 11
Unlimited OCR 2 81.5
- 12
DeepSeek-OCR 2 75.4
Source: Official OmniParseBench leaderboard
- 1
Gemini 4 Argon 96.0
- 2
Gemini 4 Carbon 95.7
- 3
Gemini 3.8 Flash 92.5
- 4 GPT-6.1 Sol 91.5
- 5 Claude Opus 5.5 90.0
- 6 Claude Sonnet 5.5 88.9
- 7 GPT-5.6 Sol 87.9
- 8 Surya OCR 2.5 85.9
- 9 OXR-1.0 85.6
- 10
MiniCPM-OCR-1.0 83.5
- 11 GLM-OCR 81.9
- 12
Unlimited OCR 2 81.5
- 13
DeepSeek-OCR 2 75.4
Sources: Official OmniParseBench leaderboard and labs’ model cards
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 96.0 | Sep 2026 | Official leaderboard | |
| 2 | | 95.7 | Oct 2026 | Official leaderboard | |
| 3 | Datalab accurate closed weights | 94.4 | Official leaderboard | ||
| 4 | Datalab balanced closed weights | 92.9 | Official leaderboard | ||
| 5 | | 92.5 | Sep 2026 | Official leaderboard | |
| 6 | GPT-6.1 Sol | 91.5 | Sep 2026 | Official leaderboard | |
| 7 | Reducto closed weights | 91.1 | Official leaderboard | ||
| 8 | LlamaParse closed weights | 90.8 | Official leaderboard | ||
| 9 | chandra-ocr-2 (Datalab) open weights, 4.5B | 90.4 | Official leaderboard | ||
| 10 | Claude Opus 5.5 | 90.0 | Sep 2026 | Official leaderboard | |
| 11 | Mistral OCR closed weights | 89.9 | Official leaderboard | ||
| 12 | Claude Sonnet 5.5 | 88.9 | Sep 2026 | Official leaderboard | |
| 13 | dots.mocr open weights, 3B | 88.2 | Official leaderboard | ||
| 14 | GPT-5.6 Sol | 87.9 | Jul 2026 | Official leaderboard | |
| 15 | Infinity-Parser2-Pro open weights, 35.1B | 87.4 | Official leaderboard | ||
| 16 | MinerU2.5-Pro open weights, 1.2B | 87.4 | Official leaderboard | ||
| 17 | Surya OCR 2.5 (Datalab) open weights, 0.7B | 86.3 | Official leaderboard | ||
| 18 | OXR-1.0 | 85.6 | Official leaderboard | ||
| 19 | OvisOCR3 open weights, 0.9B | 84.5 | Official leaderboard | ||
| 20 | | 83.5 | Oct 2026 | Official leaderboard | |
| 21 | Azure closed weights | 83.4 | Official leaderboard | ||
| 22 | Extend closed weights | 83.4 | Official leaderboard | ||
| 23 | Surya OCR 2 (Datalab) open weights, 0.7B | 83.3 | Official leaderboard | ||
| 24 | LightOnOCR-3-4B open weights, 4.5B | 83.1 | Official leaderboard | ||
| 25 | LightOnOCR-3-0.8B open weights, 0.9B | 81.9 | Official leaderboard | ||
| 26 | GLM-OCR | 81.9 | Jan 2026 | Official leaderboard | |
| 27 | | 81.5 | Oct 2026 | Official leaderboard | |
| 28 | PaddleOCR-VL-1.6 open weights, 1B | 81.3 | Official leaderboard | ||
| 29 | Nemotron 3.5 Parse open weights, 0.6B | 79.9 | Official leaderboard | ||
| 30 | Unlimited-OCR open weights, 3.3B | 79.5 | Official leaderboard | ||
| 31 | Infinity-Parser2-Flash open weights, 2.2B | 78.7 | Official leaderboard | ||
| 32 | | 75.4 | Jan 2026 | Official leaderboard | |
| 33 | Indra OCR (Datalab) open weights, 0B | 71.4 | Official leaderboard | ||
| 34 | HunyuanOCR-1.5 open weights, 1B | 68.8 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 96.0 | Sep 2026 | Official leaderboard | |
| 2 | | 95.7 | Oct 2026 | Official leaderboard | |
| 3 | | 92.5 | Sep 2026 | Official leaderboard | |
| 4 | GPT-6.1 Sol | 91.5 | Sep 2026 | Official leaderboard | |
| 5 | Claude Opus 5.5 | 90.0 | Sep 2026 | Official leaderboard | |
| 6 | Claude Sonnet 5.5 | 88.9 | Sep 2026 | Official leaderboard | |
| 7 | GPT-5.6 Sol | 87.9 | Jul 2026 | Official leaderboard | |
| 8 | OXR-1.0 | 85.6 | Official leaderboard | ||
| 9 | | 83.5 | Oct 2026 | Official leaderboard | |
| 10 | GLM-OCR | 81.9 | Jan 2026 | Official leaderboard | |
| 11 | | 81.5 | Oct 2026 | Official leaderboard | |
| 12 | | 75.4 | Jan 2026 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | 96.0 | Sep 2026 | Official leaderboard | ||
| 2 | 95.7 | Oct 2026 | Official leaderboard | ||
| 3 | 92.5 | Sep 2026 | Official leaderboard | ||
| 4 | GPT-6.1 Sol | 91.5 | Sep 2026 | Official leaderboard | |
| 5 | Claude Opus 5.5 | 90.0 | Sep 2026 | Official leaderboard | |
| 6 | Claude Sonnet 5.5 | 88.9 | Sep 2026 | Official leaderboard | |
| 7 | GPT-5.6 Sol | 87.9 | Jul 2026 | Official leaderboard | |
| 8 | Surya OCR 2.5 | 85.9 | Oct 2026 | Lab model card | |
| 9 | OXR-1.0 | 85.6 | Official leaderboard | ||
| 10 | 83.5 | Oct 2026 | Official leaderboard | ||
| 11 | GLM-OCR | 81.9 | Jan 2026 | Official leaderboard | |
| 12 | 81.5 | Oct 2026 | Official leaderboard | ||
| 13 | 75.4 | Jan 2026 | Official leaderboard |
Labs report scores for 1 model in their cards. Switch the scores above to rank them together.
Rankings by part
We read 3 parts from the benchmark’s own leaderboard: Text, Tables and Layout. Each ranks models on one part of the test. Gemini 4 Argon leads 2 of them, and Gemini 4 Carbon leads the other one. Arrows show how far a model moved from its overall rank among the models we track.
Text
12 models we track have a score here.
- 1
Gemini 4 Carbon ↑1 94.7
- 2
Gemini 4 Argon ↓1 94.4
- 3 Claude Opus 5.5 ↑2 93.9
- 4 Claude Sonnet 5.5 ↑2 93.7
- 5
Gemini 3.8 Flash ↓2 92.0
- 6 GPT-6.1 Sol ↓2 89.8
- 7 GPT-5.6 Sol 86.0
- 8 OXR-1.0 77.0
- 9
MiniCPM-OCR-1.0 73.4
- 10
Unlimited OCR 2 ↑1 73.0
Tables
12 models we track have a score here.
- 1
Gemini 4 Argon 97.1
- 2
Gemini 4 Carbon 97.1
- 3 GPT-6.1 Sol ↑1 95.6
- 4 Claude Sonnet 5.5 ↑2 95.5
- 5
Gemini 3.8 Flash ↓2 95.3
- 6 Claude Opus 5.5 ↓1 93.4
- 7 GPT-5.6 Sol 91.9
- 8
MiniCPM-OCR-1.0 ↑1 89.5
- 9 OXR-1.0 ↓1 88.3
- 10 GLM-OCR 84.7
Layout
12 models we track have a score here.
- 1
Gemini 4 Argon 96.4
- 2
Gemini 4 Carbon 95.2
- 3
Unlimited OCR 2 ↑8 91.6
- 4 OXR-1.0 ↑4 91.4
- 5
DeepSeek-OCR 2 ↑7 91.4
- 6
Gemini 3.8 Flash ↓3 90.3
- 7 GLM-OCR ↑3 89.3
- 8 GPT-6.1 Sol ↓4 89.1
- 9
MiniCPM-OCR-1.0 87.6
- 10 GPT-5.6 Sol ↓3 85.9
Number one over time Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official OmniParseBench leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Sources: Official OmniParseBench leaderboard and labs’ model cards
One lab 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.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Oct 25, 2026 | Surya OCR 2.5 | 85.9 | 85.9 on OmniParseBench |
More 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 10 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Pass Independent runs Scores from the official leaderboard (34 entries) and launch posts (1 score).
- Pass Models scored 13 models we track, plus 22 other entries on its leaderboard.
- Pass Newest score The newest is from October 2026, for Gemini 4 Carbon.
- Pass Frontier models 5 of the top 10 have a score, led by Gemini 4 Carbon (#3).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 12 rows for models we track and 22 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.