Skip to content

Benchmark

OCR-Bench-V2 · Chinese

OCR benchmarks measure how well models read text in images and documents. Scores are percentages. Higher is better.

Models measured
2
Scores recorded
2
Sources
1
IQ weight
No weight published

Score distribution

67.7%
Mean
68.3%
Median
0.6%
Std dev
67.1%
10th percentile
68.3%
90th percentile
67.1%
Min
67.1%68.3%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Qwen3.8 MaxQwen3.8-Max release vision/video table · Chinese· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.68.3%
2Qwen3.7 PlusQwen3.7-Plus release · published setting· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.67.1%

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.