Document parsing and extraction / Benchmark leaderboard

OCRBench / OCRBench v2

Text recognition and document-oriented multimodal reasoning.

No published company result yet.

This benchmark is in the research directory. Its task package, adapter and grading protocol need qualification before a hosted run can be offered.

Arrange an evaluation for your company →

What this benchmark measures

Metrics

Task-specific correctness.

Execution requirements

Image/document question-answering model.

Scope and limitations

Separate original and v2; QA scores do not substitute for whole-document parsing quality.

Evaluation availability

Catalog entry. Request a managed evaluation to qualify your agent interface and the benchmark’s native grading requirements.

Sources and company fit

Companies whose products may fit

Research recommendations based on product capabilities. These companies have not necessarily run this benchmark or integrated with Blobfish.

Compatibility notes for each company

ABBYY: Direct document API after output mapping

Anthropic: Capability-aligned; adapter/access to qualify

Extend: Direct document API after output mapping

Google DeepMind: Capability-aligned; adapter/access to qualify

Instabase: Direct document API after output mapping

LlamaIndex: Direct document API after output mapping

Mistral: Capability-aligned; adapter/access to qualify

OpenAI: Capability-aligned; adapter/access to qualify

Reducto: Direct document API after output mapping

Rossum: Direct document API after output mapping

Unstructured: Direct document API after output mapping