DROP
64 models · 11 genres
← Board
IMAGELiveRegion: CNOpen weights
⚖ Compare

Baidu

Unlimited-OCR

Current

2

shipped 2w · 26 Oct 2026

3.3B MIT-licensed open-weight vision-language OCR model for dense document, table, and formula recognition.

Specification

Current
2
Params
3.34B safetensors
License
MIT
Origin
China

Modalities: image, text

Unlimited-OCR — 6-Axis Capability Radar

HEURISTIC ESTIMATE
Unlimited-OCR77 IDX
Preset genre reference

These scores are rough estimates from category presets, catalog specs, and keywords in release notes. They are not measured benchmarks or test results. Catalog prices and context windows may refer to a different model variant.

REASONINGCODE / AGENTMULTIMODALTHROUGHPUTEFFICIENCYCONTEXT

Hover or tap an axis to inspect its estimate

Reasoning & Logic
64EVEN
Code & Tool Agency
52EVEN
Multimodal Fidelity
98+4
Speed & Throughput
82EVEN
Cost & Openness
99+21
Context & Horizon
65EVEN
RELEASE CADENCE EXPLORER

Shipping Cadence & Next Drop Forecast

WITHIN ESTIMATED INTERVAL

This is an uncalibrated estimate from limited catalog history. A ratio of 100% means one estimated interval has elapsed; it is not a probability. Next-release dates and versions remain unconfirmed.

Average Release Cadence

129 days

±7d variance
Elapsed Since Last Drop

16 days

Shipped on 2026-10-26
Annual Velocity

2.8 drops/yr

1 observed intervals · limited history
Cadence Estimate

2027-03-04

Next version: Unannounced
Elapsed / average interval: 12%88% remaining in cycle

Optional AI cadence commentary

Summarize the recorded history and its limitations. Future releases remain unconfirmed.

AUTONOMOUS ARCHITECTURAL DIFF ENGINE

Model Version Capability Delta

AI-synthesized architectural jumps, parameter scaling, and capability shifts across releases.

From:➔To:

Ready to analyze Unlimited-OCR v1 vs v2

Click Synthesize Diff to analyze latent space adjustments, resolution leaps, parameter shifts, and migration caveats via Gemini 3.8 Flash.

Version history

2 releases tracked

  1. 2

    major26 Oct 2026 · 2w

    Baidu releases Unlimited-OCR 2 open weights under MIT license on Hugging Face.

    • 3.34B vision-language OCR checkpoint (arXiv:2610.39308) with 147,000+ downloads in its first week.
    • Handles dense multi-column document parsing, mathematical formulas, and handwriting recognition.
  2. 1

    major19 Jun 2026 · 4mo

    Baidu open-sources Unlimited-OCR with 3.34B MIT-licensed weights on Hugging Face.

    • Over 4.2 million Hub downloads and 4,900+ likes since release (arXiv:2606.23050).
    • End-to-end image-text-to-text document recognition in safetensors format.

Also in Image