DeepSeek-OCR
DeepSeek-OCR.
7
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
DeepSeek-OCR
Open weights Small
No Epoch Capabilities Index score yet
- M5HisDoc -208.84% #10 /11
- MTHv2 -494.24% #10 /11
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 | |
|---|---|---|---|---|
| OCR Arena | 1,377 | #9 of 12 | Official leaderboard | |
| OmniDocBench v1.5 | 87.0 | #9 of 12 | Official leaderboard | |
| BHL OCR Eval | 6.17% | #6 of 8 | Official leaderboard | |
| M5HisDoc | -208.84% | #10 of 11 | Official leaderboard | |
| MTHv2 | -494.24% | #10 of 11 | Official leaderboard | |
| MDPBench | 51.8 | #12 of 13 | Official leaderboard | |
| olmOCR-Bench | 75.7% | #1 of 1 | Official leaderboard |
Who measured it?
Independent runs cover all 7 of its benchmarks.
- An independent run only 7
Sources: Official leaderboards, Epoch AI (CC BY 4.0) and labs’ model cards