---
title: slOCR Benchmark
emoji: 🏔️
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 5.33.0
app_file: app.py
pinned: true
fullWidth: true
license: mit
tags:
  - ocr
  - benchmark
  - leaderboard
  - vlm
  - slovenian
short_description: Slovenian-Language OCR Benchmark Leaderboard
---

# slOCR: Slovenian-Language OCR Benchmark 🏔️

A comprehensive leaderboard evaluating 20 OCR systems on 632 Slovene document pages across 6 categories: **Academic**, **Handwriting**, **Historical**, **Billboard**, **Web**, and **Textbook**.

**Models evaluated:** proprietary API systems (Claude, GPT, Gemini, Mistral), open-source VLMs (Qwen3, Kimi, InternVL, GaMS, ...), OCR-specialized models (olmOCR, Nanonets, GLM-OCR, Nemotron-Parse), and traditional pipelines (Docling, Marker, MinerU).

**Metrics:** CER, WER, BoW F1, Diacritic Micro/Macro F1, TEDS, Equation TER, Figure Recall, averaged per category into a composite Category Score and then across categories into an Overall score.

**95% confidence intervals** via 10,000-sample paired document bootstrap are available via the display mode toggle.