GLM-OCR model card (Hugging Face) Jan 30, 2026
- OmniDocBench v1.5 94.6
- OCRBench (Text) 94
GLM-OCR
GLM-OCR ranks first on 3 of the 7 benchmarks with five or more models scored.
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% #42 /44
- OCRBench 94% #1 /34
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 34 | Lab model card | |
| OmniDocBench v1.5 | 94.6 | #1 of 9 | Lab model card | |
| OmniDocBench v1.6 | 95.2 | #1 of 8 | Official leaderboard | |
| OCR Arena | 1,438 | #7 of 11 | Official leaderboard | |
| MDPBench | 67.3 | #10 of 12 | Official leaderboard | |
| OmniParseBench | 81.5 | #8 of 9 | Official leaderboard | |
| ParseBench | 29.6% | #42 of 44 | Official leaderboard |
Its lab's number next to a leaderboard
Where the benchmark's own leaderboard, or Epoch AI's run, also has this model. Gaps mostly come from different harnesses, effort levels and task subsets. Every pair.
| Benchmark | Lab says | Board says | Gap |
|---|---|---|---|
| OmniDocBench v1.5 | 94.6 OmniDocBench v1.5 Overall (Tables 3 and 4). Text Edit 0.040, Formula CDM 93.90, Table TEDS 93.96, TEDS-S 96.39, Reading Order Edit 0.044 | 94.3 Leaderboard | +0.27 |
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 Mar 11, 2026