OCRBench-V2 (zh) — leaderboard

OCRBench v2 Chinese subset: Enhanced benchmark for evaluating Large Multimodal Models on visual text localization and reasoning with Chinese text content.

Metric: Score (self-reported). Source: benchmarklist.com. Status: saturation imminent. 26 models tracked.

Top models

#ModelScore
1Qwen 3.7 Plus67.1
2Qwen 3.5 9B64.1
3Qwen 3.6 Plus63.6
4Gemini 2.5 Pro62.2
5Qwen3 Omni 30B A3B Instruct60
6Claude Opus 4.659.8
7Gemini 3.1 Pro (Preview)58.2
8GPT-5.457.7
9Ovis2-8B56
10GPT-5.252.6
11Ministral 3 14B44
12Phi-4 Multimodal Instruct37.3
13Molmo2-8B21.1

Interactive version: theaggregate.ai/benchmark?slug=ocrbench-v2-zh · How the rankings work · Data refreshed daily, snapshot 2026-07-22.