# FNC 1-p mismatch

**URL:** https://forum.numer.ai/t/fnc-1-p-mismatch/6044
**Category:** Feedback
**Created:** [January 17, 2023, 3:35pm UTC](https://forum.numer.ai/t/fnc-1-p-mismatch/6044 "2023-01-17T15:35:54Z")
**Posts on this page:** 1
**Page:** 1

<div class="post-metadata">

### Author: ![kayeffnumeraitor](https://yyz1.discourse-cdn.com/flex009/user_avatar/forum.numer.ai/kayeffnumeraitor/32/991_2.png) [@kayeffnumeraitor](https://forum.numer.ai/u/kayeffnumeraitor)
#### Post date: [January 17, 2023, 3:35pm UTC](https://forum.numer.ai/t/fnc-1-p-mismatch/6044/1 "2023-01-17T15:35:54Z")

</div>

Sorry if this is expected or a known issue, but it seems that the FNC values per round displayed on a models page are not symmetrical if the predictions are flipped (1-p for every row).

I have these models: [kayeff\_random](https://numer.ai/kayeff_random/submissions) & [modnar\_ffeyak](https://numer.ai/modnar_ffeyak/submissions). Please only look at the rounds beginning at round 370, because at earlier rounds the latter model submitted incorrect 1-p predictions. While all other metrics are the same with flipped signs, FNC is not:

 ![kayeff_random](https://canada1.discourse-cdn.com/flex009/uploads/numerai/original/2X/e/e13c9605051ed672596f7f99825d867a638af0d3.png)  
 ![modnar_ffeyak](https://canada1.discourse-cdn.com/flex009/uploads/numerai/original/2X/3/3348fce7c3229f0125bdf3757b134771d5d3faf4.png)