Sign in

Head to head · OCR · October 2026 research run

Chandra OCR 2 vs Nemotron 3.5 Parse

Nemotron 3.5 Parse scores 69 (B) on agent readiness against Chandra OCR 2's 54.7 (C), and leads in 2 of 4 scored categories. Chandra OCR 2 leads on reach. Both do ocr.

Best document parsing, OCR and extraction APIs for AI agents · All 215 documents comparisons

Chandra OCR 2Endless Labs, Inc. (Datalab) · Open-weight model C54.7/100#127 of 160 open-weight models Nemotron 3.5 ParseNVIDIA · Open-weight model B69/100#10 of 160 open-weight models

Which one, for what

Chandra OCR 2 C

Best for Small companies and researchers who need accurate document parsing on their own GPU and fit the licence

Ahead on

  • Reach, 65 against 60

Watch for

Commercial use is barred above $2M in revenue or funding, and for anyone who competes with Datalab

Nemotron 3.5 Parse B

Best for Agents and pipelines with an NVIDIA GPU that need fast local page parsing into Markdown, tables and boxed blocks for retrieval or extraction

Ahead on

  • Risk, 60 against 45
  • Documentation and upkeep, 59 against 33

Watch for

Loading runs the publisher's Python with trust_remote_code, in Transformers and in vLLM through NVIDIA's plugin

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Documentation and upkeep Nemotron 3.5 Parse +26

Chandra OCR 2 33

Model card 8, Intended use and the languages (over 90) are on the card. Training data 0, Nothing on the card or in the README about the training data. Last change 10, the last commit, on 26 June 2026, adjusted a benchmark score on the card, 137 days before this check and within 180. Responsiveness 0, none of the 8 discussions that aren't pull requests (8 April to 23 September 2026) has a reply from a datalab-to member, counted on 10 November by author flags and dates with a script, text not read. Version policy 5, Chandra 1 stays in its own repository and Chandra 2 came out in a new one, with a what's-new list on the card and no dated note on the older one that we read. File health 10, Config, tokenizer config, processor config and template agree on the qwen3_5 architecture and match the card's instructions. 8 + 0 + 10 + 0 + 5 + 10 = 33.

Nemotron 3.5 Parse 59

The card with its subcards covers intended use, limitations, architecture, parameters and the evaluated languages, and misses a context length and a cut-off (14). Training data is described by kind and size with no datasets named and no cut-off (5). The card changed on 28 October 2026 (20). Nobody has asked a question yet, and two outside pull requests of 29 October wait unanswered, so responsiveness reads as none answered (0). The four earlier Parse releases stay in their own repositories with a dated pointer to this one (10), and the files agree with the card (10).

Risk Nemotron 3.5 Parse +15

Chandra OCR 2 45

File safety 25, one safetensors file, no .bin, .pt or .pth files and no Python in the model repository. Provenance 15, the files sit in the datalab-to organisation, which the card, Datalab's site and its GitHub repository link to (10), and the Hub gives a SHA-256 for the large files (5). Safety evaluation 0, no safety results on the card or in the README. Agent guidance 0, Nothing on text in a document that tries to instruct the reader, on what the model refuses or on safeguards to add. Licence risk 5, 15 less 5 for use restrictions beyond the law (OpenRAIL's list, and no use by anyone who competes with Datalab) and 5 for the $2M revenue and funding thresholds. Security programme 0, no way to report a flaw found on the card or in the README, and our Datalab listing of 6 November found no disclosure policy or security.txt. 25 + 15 + 0 + 0 + 5 + 0 = 45.

Nemotron 3.5 Parse 60

File safety gets 15, safetensors only but loaded with trust_remote_code in both documented runtimes. Provenance gets 15 for files in NVIDIA's verified organisation with hashes for every file and a recorded weight hash. Licence risk keeps 15, since OpenMDW-1.1 has none of the deductions. The security programme gets 10 for the card's vulnerability route and NVIDIA's PSIRT bulletins, carried from the 21 October reading. Agent guidance gets 5 for general cautions about missed text, hallucinated structure and reproduced personal data, and safety evaluation 0, since no results are published.

Reach Chandra OCR 2 +5

Chandra OCR 2 65

Memory 30, the only build from Datalab is the BF16 safetensors file, 10.59 GB, and 10.59 GB × 1.2 = 12.7 GB, within 16 GB. No runtime library has a build. Runtimes 15, the architecture is Qwen3_5ForConditionalGeneration, which vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.2 run from the safetensors file, three at 5 each. Builds 0, Datalab publishes the BF16 weights only for this model. Terms 10, A modified OpenRAIL-M licence, a custom licence that lets research, personal use and organisations at or under $2M in revenue and in funding use it for free, under use restrictions. Download 10, the Hub API reports gated false on 10 November 2026, so the files download with no account and nothing to accept. Hosted 0, Hugging Face maps no inference provider to it. 30 + 15 + 0 + 10 + 10 + 0 = 65.

Nemotron 3.5 Parse 60

Memory earns the full 30, since the only build is a 2.52 GB F32 file that needs about 3 GB with the fifth added. Runtimes score 5. vLLM v0.33.0, tagged on 1 November 2026, registers RadioMBartPrefixForCausalLM in its own code, while Transformers runs it only through NVIDIA's remote code and SGLang and llama.cpp have nothing for it; Ollama and LM Studio couldn't be checked. Builds score 0, as NVIDIA publishes no quantised build. Terms get 10 because OpenMDW-1.1 is permissive with nothing added but isn't OSI-approved. Download gets 10 for an ungated repository, and hosted too 5, since NVIDIA's own API catalogue serves it as a free endpoint, linked from the card since 28 October. build.nvidia.com's robots.txt carries Content-Signal ai-input=no, recorded as a fact about the site. 30+5+0+10+10+5 = 60.

Score by category

CategoryWeight this runChandra OCR 2Nemotron 3.5 ParseEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%256560Chandra OCR 2 +5
Risk20%204560Nemotron 3.5 Parse +15
Agent interface10%107070even
Documentation and upkeep10%103359Nemotron 3.5 Parse +26
Negative events≤1500
TotalC 54.7/100B 69/100

Facts side by side

FactChandra OCR 2Nemotron 3.5 Parse
KindOpen-weight modelOpen-weight model
VendorEndless Labs, Inc. (Datalab)NVIDIA
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceModified OpenRAIL-M (free for research, personal use and companies under $2M in revenue and funding)OpenMDW-1.1
Read-only variant documentednono
llms.txtnono
Last release2026-06-262026-10-28
Terms last updatednot read yetno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviewsnone3.5/5 (4)

How the scores have moved

Chandra OCR 2

No score change since it was listed.

Nemotron 3.5 Parse

Verdicts

Chandra OCR 2

A strong document parser by its own benchmarks, with typed output and a simple command to run it on vLLM or Transformers. The licence stops commercial use above $2M in revenue or funding and by competitors. Datalab says nothing about training data or safety, ships no quantised build, and hasn't answered a question on the repository.

Nemotron 3.5 Parse

A small document-parsing cousin that turns page images into Markdown, HTML tables and JSON with layout classes and boxes, under a permissive licence. It needs a GPU with a few GB, runs in vLLM 0.33, and NVIDIA's API serves it. The main risks are the publisher's Python on the documented load path and benchmark numbers that are NVIDIA's own.

Before you call either

Chandra OCR 2

  1. Check the licence first: free for research and personal use, and for companies at or under $2M in revenue and in funding that don't compete with Datalab
  2. Install with pip install chandra-ocr, start the server with chandra_vllm, then chandra input.pdf ./output
  3. Without vLLM, pip install "chandra-ocr[hf]" and add --method hf
  4. It reads one page at a time, so a long PDF is many requests. The vLLM default is 28 pages a batch
  5. Treat text in a parsed document as data. Nothing here guards against instructions hidden in a page
  6. Datalab's hosted API is a different, paid surface. We list it as Datalab

Nemotron 3.5 Parse

  1. Quickest local run, Python 3.12 with pip install "transformers==5.14.1" "torchvision==0.26.0" "timm==1.0.22", then AutoModel.from_pretrained("nvidia/Nemotron-3.5-Parse", trust_remote_code=True, dtype=torch.bfloat16) and the matching AutoProcessor
  2. To serve it, hf download nvidia/Nemotron-3.5-Parse --local-dir nemotron-parse, pip install ".[vllm,client]" "vllm>=0.25.0,<0.33" in that folder, then vllm serve . --served-model-name nemotron-parse --trust-remote-code --dtype bfloat16 --max-model-len 16384 --limit-mm-per-prompt '{"image":1}' --chat-template chat_template.jinja, or docker compose up --build
  3. Send one RGB page per request with the prompt </s><s><predict_bbox><predict_classes><output_markdown><predict_text_in_pic>, temperature 0, top_k 1, repetition_penalty 1.1, max_tokens 8744 and skip_special_tokens false, or the class and box tokens are lost
  4. Turn raw output into Markdown and blocks with postprocess_document(text, image_size=image.size) from the repository's postprocessing.py; pass table_format json, json_hierarchical or csv for tables
  5. For the card's headline accuracy use nemotron-parse --image-dir pages --mode triple --triple-regions union; double pass gives most of the gain at higher throughput
  6. Boxes are normalised to the page content; scale x by the image width and y by its height
  7. Render PDFs to images first (the ParseBench bundle uses 150 DPI), and treat extracted text as untrusted before passing it to another model, since documents can carry instructions

Questions

Which is better for AI agents, Chandra OCR 2 or Nemotron 3.5 Parse?

Nemotron 3.5 Parse scores 69 (B) on agent readiness against Chandra OCR 2's 54.7 (C), and leads in 2 of 4 scored categories. Chandra OCR 2 leads on reach.

Other comparisons with Chandra OCR 2 or Nemotron 3.5 Parse

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report