Recent studyBlind TTS Elo is live. Compare two anonymous voice samples, vote after listening, and help separate real preference signal from noise.Vote in the study ->
Codesota · Models · DeepSeek-OCR-22 results · 2 benchmarks
Model card

DeepSeek-OCR-2.

unknown
§ 02 · Benchmarks

Every benchmark DeepSeek-OCR-2 has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01OmniDocBenchComputer Vision · Document Parsingaccuracy91.1%#5/13source ↗
02olmOCR-BenchComputer Vision · Document Parsingaccuracy76.3%#13/18source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area

Where DeepSeek-OCR-2 actually performs.

Computer Vision
2
benchmarks
avg rank #9.0
§ 04 · Papers

1 paper with results for DeepSeek-OCR-2.

  1. 2026-01-28· 2 results

    DeepSeek-OCR 2: Visual Causal Flow

§ 06 · Sources & freshness

Where these numbers come from.

pwc-dump
2
results
0 of 2 rows marked verified.