GlotOCR Bench: 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 scripts and averaged over the three resource tiers; higher is better.

Metric: Acc@5 (%): share of sentences transcribed with CER at most 0.05, 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); 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 Lite61.9#371
2Dots.mocr59.6
3dots.ocr59.3
4HunyuanOCR54.2
5Qwen 3 VL 8B52.4#917
6olmOCR-251.5
7RolmOCR50.6
8GPT-4.150.5#505
9LightOnOCR-247.4
10Nanonets-OCR246.6
11PaddleOCR-VL-1.543.5
12FireRed-OCR43.4
13GLM-OCR39.8
14DeepSeek-OCR-238.7

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