如果你对多语言OCR或印地语文本识别感兴趣，这篇论文揭示了主流模型在天城体上的真实差距，尤其是GPT-5.5表现不如开源Qwen3-VL-8B。
该论文对10个OCR系统在天城体（印地语）上进行基准测试，包括EasyOCR、Qwen2.5-VL-3B、Qwen3-VL-8B、DeepSeek-OCR、Gemini 2.5 Flash、Claude Opus 4.7、GPT-5.5等。在清洁文本上所有系统chrF++在91-98之间，但在真实扫描图像中，9个系统性能大幅下降（EasyOCR从93.6跌至58.3）。Qwen3-VL-8B（75.2，可在单张24GB GPU运行）超过GPT-5.5（58.5）和olmOCR-7B（40.5），Gemini和Claude领先（86.3和82.2）。论文还提出基于ByT5的字节级后校正器可将廉价引擎chrF++提升1.2-1.5。
Can OCR-VLMs Read Devanagari? A Stress-Test Benchmark and Post-Correction Study
OCR systems, ranging from classical engines to specialised OCR vision-language models (OCR-VLMs) and frontier multimodal LLMs, report strong results on English and Chinese document benchmarks, yet their behaviour on Indic scripts is largely uncharacterised. We benchmark ten systems on Devanagari (Hindi): classical EasyOCR; open VLMs (Qwen2.5-VL-3B, Qwen3-VL-8B, olmOCR-7B); specialised OCR-VLMs (DeepSeek-OCR, Unlimited-OCR); and frontier closed models (Gemini 2.5 Flash, Claude Opus 4.7, GPT-5.5, Mistral OCR), across four synthetic degradation conditions and 300 real printed scans. We report four findings. First, on clean rendered text all ten cluster within chrF++ 91 to 98, so synthetic text does not separate them. Second, under degradation the specialised OCR-VLMs are the most fragile: DeepSeek-OCR suffers rare but catastrophic repetition failures (outputs up to 71 the reference length) that wreck its corpus mean even though its median is the best of any system, which is why we report median and catastrophic-rate instead of the mean. Third, on real scans nine of the ten systems collapse (EasyOCR falls from chrF++ 93.6 to 58.3) and the field spreads across a 76-point range, so synthetic renders badly overstate Devanagari quality. Fourth, strong English OCR does not predict Indic OCR: GPT-5.5 drops to chrF++ 58.5 (tying classical EasyOCR) and olmOCR-7B, the model behind olmOCR-Bench, falls to 40.5, while the open Qwen3-VL-8B (75.2, runnable on a single 24 GB GPU) beats GPT-5.5 and approaches Mistral; Gemini and Claude lead at 86.3 and 82.2. An error taxonomy separates surface errors (numerals, punctuation) from structural ones (conjuncts, matras, nukta), and a byte-level (ByT5) post-corrector improves a cheap engine on its own error distribution (chrF++ +1.2 to +1.5) but does not transfer across engines. We release the benchmark, code, and models.