# ner.eval-ab input : should that be the same text as the evaluation dataset?
**URL:** https://support.prodi.gy/t/ner-eval-ab-input-should-that-be-the-same-text-as-the-evaluation-dataset/1001
**Category:** Uncategorized
**Tags:** usage, ner
**Created:** [November 29, 2018, 8:28pm UTC](https://support.prodi.gy/t/ner-eval-ab-input-should-that-be-the-same-text-as-the-evaluation-dataset/1001 "2018-11-29T20:28:50Z")
**Posts on this page:** 2
**Page:** 1
### Author:  [@Arul](https://support.prodi.gy/u/Arul)
#### Post date: [November 29, 2018, 8:28pm UTC](https://support.prodi.gy/t/ner-eval-ab-input-should-that-be-the-same-text-as-the-evaluation-dataset/1001/1 "2018-11-29T20:28:50Z")
I am trying to compare two models. I have a gold evaluation dataset.
`prodigy ner.eval-ab gold_eval_500 trained_model1 trained_model1`
This seems to expect input data from stdin. I expected the input text considered to evaluate will be from the evaluation dataset. should i seperate out the texts from the evaluation set and give as input text?
---
### Author:  [@ines](https://support.prodi.gy/u/ines)
#### Post date: [November 30, 2018, 1:13pm UTC](https://support.prodi.gy/t/ner-eval-ab-input-should-that-be-the-same-text-as-the-evaluation-dataset/1001/2 "2018-11-30T13:13:38Z")
Hi! Sorry if this was confusing – the idea of the `ner.eval-ab` recipe is that it lets you run a quick “live evaluation” with two models, by comparing the output on the given input data.
So instead of having to create the gold-standard evaluation set from scratch, you can quickly click through a bunch of examples and already get an idea of how your models are performing. Because the feedback you give is _binary_ (e.g. green or red), the evaluation process also lets you capture which analysis is _better_ and which model’s output you or the annotator _preferred overall_. Even two models with similar accuracy scores can produce different parses – and one model’s analysis could be much better thant the other’s, even if they both make the same amount of mistakes in total.
tl;dr: Yes, the quickest way to use `ner.eval-ab` would probably be to extract the texts from your existing set and load it in as the input data (fourth argument) and use a new dataset to store the new AB annotations you create with the recipe. I’d recommend starting off with a few hundred AB annotations and repeating the process every once in a while as you update and train new models 🙂