Multimodal & Grounded benchmark
CC-OCR leaderboard
Every model the catalog carries a published CC-OCR value for, ranked by that value.
CategoryMultimodal & Grounded
MeasureText extraction from images and documents
TasksOptical character recognition
DifficultyDocument reading
Published byQwen3.6 launch benchmarks
An OCR-focused benchmark for reading and extracting text from visually complex documents and images.
CC-OCR ranking
3 models with a published CC-OCR value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Text extraction from images and documents |
|---|---|---|---|
| 1 |  Qwen3.6-35B-A3B | Alibaba | 81.9 |
| 2 | Qwen3.6-27B | Alibaba | 81.2 |
| 3 | Qwen3.8 Max | Alibaba | 79.6 |
Evidence key: Observed
Rows are ordered by the value Qwen3.6 launch benchmarks published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.