# Leaderboard performance **URL:** \ **Category:** Warm Up: Machine Learning with a Heart\ **Created:** [May 23, 2019, 8:11am UTC](https://community.drivendata.org/t/leaderboard-performance/3423 "2019-05-23T08:11:21Z")\ **Posts on this page:** 4\ **Page:** 1
**Author:** ![neatdot](https://avatars.discourse-cdn.com/v4/letter/n/7bcc69/32.png) [@neatdot](https://community.drivendata.org/u/neatdot)\ **Post date:** [May 23, 2019, 8:11am UTC](https://community.drivendata.org/t/leaderboard-performance/3423/1 "2019-05-23T08:11:21Z")
Anyone have a view on the top couple of leaderboard entries? I can conceive of some people getting a result in the 0.2 range, but the top 2 scores look distinctly odd, and I just don’t believe the value of 0 for the person in first place. ---
**Author:** ![Gillesvdw](https://avatars.discourse-cdn.com/v4/letter/g/a8b319/32.png) [@Gillesvdw](https://community.drivendata.org/u/Gillesvdw)\ **Post date:** [May 30, 2019, 7:51am UTC](https://community.drivendata.org/t/leaderboard-performance/3423/2 "2019-05-30T07:51:24Z")
You’re correct to not believe that value. Since this dataset is taken from the UCI (public) repository, I am pretty sure that the number one on the leaderboard just grabbed the labels for the test set from there. ---
**Author:** ![apalladi](https://yyz2.discourse-cdn.com/flex028/user_avatar/community.drivendata.org/apalladi/32/818_2.png) [@apalladi](https://community.drivendata.org/u/apalladi)\ **Post date:** [June 28, 2019, 2:09pm UTC](https://community.drivendata.org/t/leaderboard-performance/3423/3 "2019-06-28T14:09:37Z")
I agree with you. Values of the log-loss so low look suspicious. In principle you may have a perfect model on the training set, with a log-loss close to 0. However it is quite unlikely to have the same log-loss also applying the model to the test set. ---
**Author:** ![grandia](https://avatars.discourse-cdn.com/v4/letter/g/41988e/32.png) [@grandia](https://community.drivendata.org/u/grandia)\ **Post date:** [July 28, 2019, 2:15pm UTC](https://community.drivendata.org/t/leaderboard-performance/3423/4 "2019-07-28T14:15:01Z")
There’s only 90 predictions to be made. With enough trial and error, you can sort of infer what the correct predictions are