Results seem to be much worse than those output by a bidaf graph not trained on multi paragraph

I have been messing around with this project and I have found that the results don't seem to be in anywhere near as good as the bidaf model.

For example if we compare answers from question and document pairs at
http://demo.allennlp.org/machine-comprehension and https://documentqa.allenai.org/ we see that this project preforms alot worse, and seems to much prefer shorter answers.

## Examples
#### Example 1
**paragraph:**
Robotics is an interdisciplinary branch of engineering and science that includes mechanical engineering, electrical engineering, computer science, and others. Robotics deals with the design, construction, operation, and use of robots, as well as computer systems for their control, sensory feedback, and information processing. These technologies are used to develop machines that can substitute for humans. Robots can be used in any situation and for any purpose, but today many are used in dangerous environments (including bomb detection and de-activation), manufacturing processes, or where humans cannot survive. Robots can take on any form but some are made to resemble humans in appearance. This is said to help in the acceptance of a robot in certain replicative behaviors usually performed by people. Such robots attempt to replicate walking, lifting, speech, cognition, and basically anything a human can do.
**question**
What do robots that resemble humans attempt to do?
**answer from http://demo.allennlp.org/machine-comprehension**
replicate walking, lifting, speech, cognition
**answer from https://documentqa.allenai.org/**
walking

#### Example 2
**paragraph**
The Matrix is a 1999 science fiction action film written and directed by The Wachowskis, starring Keanu Reeves, Laurence Fishburne, Carrie-Anne Moss, Hugo Weaving, and Joe Pantoliano. It depicts a dystopian future in which reality as perceived by most humans is actually a simulated reality called "the Matrix", created by sentient machines to subdue the human population, while their bodies' heat and electrical activity are used as an energy source. Computer programmer "Neo" learns this truth and is drawn into a rebellion against the machines, which involves other people who have been freed from the "dream world."
**question**
Who stars in The Matrix?
**answer from http://demo.allennlp.org/machine-comprehension**
Keanu Reeves, Laurence Fishburne, Carrie-Anne Moss, Hugo Weaving, and Joe Pantoliano
**answer from https://documentqa.allenai.org/**
Keanu Reeves

Do you guys know why this might be ?