‹ PublicAI Index
The LLM benchmark aggregator.
WeVisDoc 2B
Other · 2B
Strongest in Document parsing (#72 of 77), weakest in Knowledge (#186 of 191). Above par in 0 of 2 scopes. Among the models it meets almost everywhere, it finishes behind Claude Opus 5.5 and Claude Fable 5.1 and ahead of Granite Vision 4.1 4B and Qwen3.5 2B.
§ 1 · Profile
What it is good at
Bars run from 50 — the average of the models each source lists — so right of the line is above par. The middle column is the gap to whoever leads that scope.
Knowledge37.3−25.4#186/1911/3
Document parsing36.5−27.1#72/771/1
§ 2 · Head to head
What it beats, and what beats it
The same models turn up scope after scope. Counted once: where both were placed, who finished higher. Bars run right for WeVisDoc 2B, left for the other.
§ 3 · Sources
Where the numbers come from
1 publication, 6 figures. Every one links to the page it was read from.
ParseBench · Overall 38.93%ParseBench · Tables 70.41%ParseBench · Charts 0.86%ParseBench · Content faithfulness 77.11%ParseBench · Semantic formatting 46.28%ParseBench · Visual grounding 0%
Badge
[](https://publicai.io/model-index/m/wevisdoc-2b)