GlotOCR Bench - Character Error Rate: 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. Character error rate in percent, macro-averaged over scripts and averaged over the high, mid and low-resource tiers; lower is better.

Metric: Character error rate (%, capped at 100), macro-averaged over scripts, mean of the high (Latin), mid (9 scripts) and low-resource (148 scripts) tiers, 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); lower 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 Lite27.7#371
2dots.ocr29.7
3Dots.mocr30.5
4GPT-4.131.7#505
5HunyuanOCR32.3
6Qwen 3 VL 8B33#917
7olmOCR-233.5
8RolmOCR34.7
9Nanonets-OCR235.5
10LightOnOCR-235.6
11FireRed-OCR38.2
12DeepSeek-OCR-240.6
13PaddleOCR-VL-1.541.1
14GLM-OCR41.5

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-character-error-rate · How It Works · Data refreshed daily, snapshot 2026-11-21.