Skip to content

Benchmark

OCRBench-V2 (zh)

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

Models measured
6
Scores recorded
8
Sources
1
IQ weight
0.44

Score distribution

60.7%
Mean
61.2%
Median
1.7%
Std dev
59.2%
10th percentile
62.1%
90th percentile
57.8%
Min
57.8%63.5%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.44 for chat models, measured over 6 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Qwen3 VL 235Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.63.5%
2Qwen3 VL 32B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.62.1%
3Qwen3 VL 235B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.61.8%
4Qwen3 VL 8B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.61.2%
5qwen3-vl-30bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.60.4%
6Qwen: Qwen3 VL 8B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.59.2%
7Qwen3 VL 32B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.59.2%
8qwen3-vl-30b· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.57.8%

Data credits: Data by LLM Stats