GLM-OCR model card (Hugging Face) 30 Jan 2026
- OmniDocBench v1.5 94.6
- OCRBench (Text) 94
GLM-OCR
GLM-OCR ranks first on 3 of the 7 benchmarks it has scores on.
7
Benchmarks with a score
3
Ranked first, out of five or more models
3
In the top three
Z.ai Jan 2026
GLM-OCR
Open weights Small
No Epoch Capabilities Index score yet
- ParseBench 29.6% #40 /42
- OCRBench 94% #1 /28
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OCRBench | 94% | #1 of 28 | Model card | |
| OmniDocBench v1.5 | 94.6 | #1 of 13 | Model card | |
| OmniDocBench v1.6 | 95.2 | #1 of 7 | Official leaderboard | |
| OCR Arena | 1,421 | #7 of 11 | Official leaderboard | |
| MDPBench | 67.3 | #7 of 9 | Official leaderboard | |
| ParseBench | 29.6% | #40 of 42 | Official leaderboard | |
| OmniParseBench | 81.5 | #6 of 6 | Official leaderboard |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.
Its system card
Every result in the longer documents the lab published with it.
GLM-OCR Technical Report 11 Mar 2026