Benchmark Almanac

Unlimited OCR 2

Unlimited OCR 2 ranks first on 2 of the 5 benchmarks with five or more models scored.

Baidu Released October 27th, 2026 Family Unlimited OCR The lab's model card Compare with others
6
Benchmarks with a score
2
Ranked first, out of five or more models
2
In the top three
Baidu Oct 2026

Unlimited OCR 2

Open weights Small

No Epoch Capabilities Index score yet
  • MarathonDocBench 77.1% #1 /9
  • ParseBench 57.1% #32 /48
  • ParseBench-2 65.5% #17 /21

Where has it been number one?

Unlimited OCR 2 is number one on 2 benchmarks today.

Source: Official leaderboards

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

BenchmarkScoreRankSource
MarathonDocBench 77.1% #1 of 9 Official leaderboard
BHL OCR Eval 3.29% #1 of 8 Official leaderboard
ParseBench 57.1% #32 of 48 Official leaderboard
ParseBench-2 65.5% #17 of 21 Official leaderboard
OmniParseBench 81.5 #11 of 12 Official leaderboard
MPDocBench-Parse 84.6% #1 of 1 lab number Lab model card

Who measured it?

Independent runs cover 5 of its 6 benchmarks. For the other 1, we have only Baidu's own number or a claim Epoch AI collected.

  • An independent run and a claim 1
  • An independent run only 4
  • A claim only 1
Official leaderboards scored it on 5.

Sources: Official leaderboards, Epoch AI (CC BY 4.0) and labs’ model cards

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
MarathonDocBench 77.1% MarathonDocBench Overall 77.1% Leaderboard Same

Its launch post

The benchmarks the lab chose to headline, with the scores it gave.