GlotOCR Bench - Latin Script: 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 Latin-script sentences with character error rate at most 5 percent; higher is better.

Metric: Acc@5 (%): share of sentences transcribed with CER at most 0.05, macro-averaged over scripts, high-resource tier (Latin script), 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 February 2027. 14 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 3.1 Flash Lite95.3#371
2Dots.mocr93.1
3dots.ocr91.8
4olmOCR-290.5
5LightOnOCR-289.8
6RolmOCR89.6
7Qwen 3 VL 8B89.5#917
8GLM-OCR89.5
9Nanonets-OCR288.6
10HunyuanOCR85.3
11FireRed-OCR83.6
12GPT-4.183.2#505
13PaddleOCR-VL-1.579.8
14DeepSeek-OCR-276.2

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-latin-script · How It Works · Data refreshed daily, snapshot 2026-11-21.