OCRBench

Reported in recent model launches

These model reports include this benchmark. Their harnesses, task subsets, scoring policies, and resource budgets can differ; follow each report’s evaluation notes before joining the numbers.

What it measures

Text-rich visual tasks test recognition and understanding of writing inside images.

How to read the result

Inspect recognition failures separately from reasoning over correctly recognized text.

Limits and comparison traps

Resolution, cropping and benchmark version affect visibility and scoring. Keep original OCRBench and later revisions distinct.

Benchmark reference notes

Comprehensive evaluation of scene text recognition, handwritten text, mathematical formula OCR, table parsing, and key information extraction.

Where this fits in an evaluation suite

Ask what the task actually requires: recall, deduction, search, or a mixture. Separate closed-book reasoning from retrieval and tool-assisted problem solving.

Start with a capability hypothesis, then choose a second test with a different failure mode. Keep the checkpoint, reasoning effort, agent tools, sampling policy, and scoring procedure fixed when measuring a training intervention. Record failures and missing outputs in the denominator.

A reproducible comparison

Pin the benchmark release, task split, model configuration, tools, sampling budget, and evaluation harness described by the primary source.

Publish the exact run configuration, item coverage, score units, and available uncertainty. If a source supplies only an aggregate or a single run, preserve that limit. A new model name or a rounded score alone does not establish a capability improvement.