Leaderboard

Current

Live standings from the Kaggle public leaderboards

OverviewTaskTimelineRulesParticipateLeaderboardPublicationsOrganisersFAQ
0.676
Best BalAcc@10
14
Teams
138
Submissions
Days remaining
Metric:

Teams by BalAcc@10

Top-10 balanced accuracy on the 50-word vocab — Kaggle’s official public score

1Umur Yıldız
0.6761
2JovanaLab
0.6123
3kakuteki
0.5987
4MindLink
0.5720
5titus fisher
0.5097
6Alireza Karimi
0.4797
7Baseline
0.4444
8Brain King
0.3520
9SHINE
0.3016
10monte-carlo
0.2900
11MindReaders2.0
0.2756
12Kim
0.2292
13lavender_lover
0.1906
14Viknesh .V
0.1600

Best score per team — every metric

Kaggle ranks one number. We archive every submission and re-score it ourselves, so each team's best on each metric sits side by side (public split). Click a metric to rank by it.

#TeamBalAcc@10 BalAcc@1 OVMI Subs
1Umur Yıldız
0.6761
0.2233
1.1230
12
2JovanaLab
0.6123
0.2498
1.0382
9
3kakuteki
0.5987
0.1911
1.0715
36
4MindLink
0.5720
0.1594
0.9749
14
5titus fisher
0.5097
0.0740
0.8982
10
6Alireza Karimi
0.4797
0.1140
0.9574
16
7Baseline
0.4444
0.0733
0.9803
1
8Brain King
0.3520
0.0724
0.9137
6
9SHINE
0.3016
0.0400
0.9437
2
10monte-carlo
0.2900
0.0483
0.4671
5
11MindReaders2.0
0.2756
0.0645
0.9441
19
12Kim
0.2292
0.0278
0.0599
4
13lavender_lover
0.1906
0.0200
0.4893
3
14Viknesh .V
0.1600
0.0200
0.0000
1

About these numbers

BalAcc@10 is Kaggle's official public score, shown here exactly as Kaggle reports it. BalAcc@1 (strict top-1) and OVMI (the information a decoder recovers over the vocabulary) are computed by us from the submitted files, on the same public split — final placements use the private split, revealed after the deadline.

Updated · Deep Track on Kaggle →