GlotOCR Bench - Low-Resource Scripts: leaderboard

Multilingual OCR on GlotOCR Bench (2026): sentences from real multilingual text in 158 Unicode scripts are rendered as clean images and transcribed zero-shot. Share of sentences with character error rate at most 5 percent, macro-averaged over 148 low-resource scripts; higher is better.

Metric: Acc@5 (%): share of sentences transcribed with CER at most 0.05, macro-averaged over scripts, low-resource tier (148 scripts), on GlotOCR Bench (16,375 real multilingual sentences rendered as clean images across 158 Unicode scripts; zero-shot transcription; CER is the character edit distance with whitespace ignored, capped at 1, best of four output normalizations); higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 14 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 3.1 Flash Lite7.7#371
2dots.ocr7.7
3Dots.mocr7.7
4HunyuanOCR3.4
5PaddleOCR-VL-1.52
6GPT-4.11.6#505
7Qwen 3 VL 8B0.8#917
8LightOnOCR-20.7
9DeepSeek-OCR-20.3
10olmOCR-20.3
11FireRed-OCR0.2
12RolmOCR0.2
13Nanonets-OCR20.2
14GLM-OCR0

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=glotocr-bench-low-resource-scripts · How It Works · Data refreshed daily, snapshot 2026-11-21.