DeepSeek-OCR 2
DeepSeek-OCR 2 places in the top three on OmniDocBench v1.5.
4
Benchmarks with a score
0
Ranked first, out of five or more models
1
In the top three
DeepSeek Jan 2026 DeepSeek-OCR 2
Open weights Mid-size
No Epoch Capabilities Index score yet
- ParseBench 41.2% #36 /44
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 | |
|---|---|---|---|---|
| OmniDocBench v1.5 | 91.1 | #2 of 9 | Lab model card | |
| OmniDocBench v1.6 | 90.3 | #4 of 8 | Official leaderboard | |
| ParseBench | 41.2% | #36 of 44 | Official leaderboard | |
| OmniParseBench | 75.2 | #9 of 9 | 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 | 91.1 OmniDocBench v1.5 Overall 91.09, V-token max 1120, Text Edit 0.048, Formula CDM 90.31, Table TEDS 87.75, Table TEDS-S 92.06, R-order Edit 0.057 (Table 1) | 89.2 Leaderboard | +1.92 |
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.
DeepSeek-OCR 2: Visual Causal Flow Jan 28, 2026
Capabilities
- OmniDocBench v1.5 91.1