Leaderboard

Current

Live standings from the Kaggle public leaderboards

Overview Task Timeline Rules Participate Leaderboard Publications Organisers FAQ

BAcc@10 over time

Each dot is a team improving its own best public BAcc@10 score; the stepped line follows the best score overall. Hover a dot for the team.

team improves its own bestnew best overallstate of the art

0.727

Best BalAcc@10

Teams

1,502

Submissions

—

Days remaining

Metric:

Teams by BalAcc@10

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

1Varshith Madishetty

0.7265

2MindLink

0.7212

3titus fisher

0.7173

4Umur Yıldız

0.7148

5ottietjesesakfs

0.7112

6Connor Finnerty

0.6955

7Infera-Neuro

0.6786

8Kim

0.6752

9Munich Logic Lab

0.6729

10Jordan Griffith

0.6694

11CWBZ

0.6601

12dav0dea

0.6563

13JovanaLab

0.6558

14MagnetoLex

0.6548

15kakuteki

0.6463

16neural2speech

0.6447

17Brain King

0.6441

18Jatin Arutla

0.6439

19Michal

0.6438

20@Arnauya

0.6428

Showing top 20 of 44 teams — full standings in the table below.

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.

#	Team	BalAcc@10 ↓	BalAcc@1	OVMI	Subs
1	Varshith Madishetty	0.7265	0.2889	1.1422	72
2	MindLink	0.7212	0.2539	1.1265	158
3	titus fisher	0.7173	0.2680	1.1175	101
4	Umur Yıldız	0.7148	0.2432	1.1690	110
5	ottietjesesakfs	0.7112	0.2587	1.1591	140
6	Connor Finnerty	0.6955	0.2552	1.1444	62
7	Infera-Neuro	0.6786	0.2157	1.1512	55
8	Kim	0.6752	0.2187	1.0464	88
9	Munich Logic Lab	0.6729	0.1997	1.0832	35
10	Jordan Griffith	0.6694	0.2386	1.1628	28
11	CWBZ	0.6601	0.2089	1.1239	33
12	dav0dea	0.6563	0.2251	1.1486	21
13	JovanaLab	0.6558	0.2729	1.0757	26
14	MagnetoLex	0.6548	0.2173	1.1227	39
15	kakuteki	0.6463	0.2239	1.1474	47
16	neural2speech	0.6447	0.1447	1.1265	10
17	Brain King	0.6441	0.1522	1.1299	70
18	Jatin Arutla	0.6439	0.2387	1.0920	16
19	Michal	0.6438	0.1418	1.0159	3
20	@Arnauya	0.6428	0.1899	1.1423	81
21	SENPAI	0.6296	0.1858	1.0606	61
22	onlytry	0.6152	0.1934	1.0748	9
23	Artem Blanar	0.5896	0.1831	1.0056	42
24	duck2bin2	0.5554	0.1420	0.8604	4
25	syouya tobita	0.5515	0.1210	1.1454	13
26	Baseline	0.4444	0.0733	0.9803	1
27	Sia	0.4362	0.1014	0.9362	5
28	Shuntaro Suzuki	0.3540	0.0488	0.8104	5
29	liuyishj	0.3343	0.0490	0.7152	9
30	AutoDecode	0.3338	0.0775	1.0790	19
31	MindReaders2.0	0.3322	0.0740	0.9441	78
32	Jun Jie Li	0.3176	0.0864	0.8436	12
33	peperonata	0.3066	0.0323	0.7890	4
34	monte-carlo	0.2900	0.0483	0.4671	5
35	Salsinats	0.2883	0.0319	0.5788	9
36	Bhargav Kowshik	0.2871	0.0292	1.0947	16
37	Fon1as	0.2538	0.0249	0.2581	1
38	lsumin12	0.2488	0.0329	0.3084	1
39	willguido	0.2444	0.0244	0.1239	4
40	Nguyen Anh	0.2164	0.0311	0.5181	3
41	Shriya Patkar	0.1950	0.0245	0.1998	1
42	lavender_lover	0.1906	0.0200	0.4893	3
43	LizaSheina	0.1880	0.0284	0.3681	1
44	Viknesh .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 →