Leaderboard

Current

Final public standings from the Kaggle leaderboards

Overview Task Timeline Rules Participate Leaderboard Submit Papers Publications Organisers FAQ

Submissions have closed. These are the public leaderboard standings. Final rankings use a separate holdout set and are subject to verification, and Kaggle's private leaderboard is not the final outcome. We aim to announce the winners by 1 December 2026. To see how a new model would have scored, use the submission page. Verification details →

Leaderboard notice: Some Broad track leaderboard scores may be affected by cross-track leakage, but final rankings will be code-checked and unaffected by this issue. Using metadata such as word_onset_s or shuffle_seed to map predictions between tracks will not be permitted in the final evaluation. Read the full announcement →

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

0.813

Best BalAcc@10

Teams

4,855

Submissions

—

Days remaining

Metric:

Teams by BalAcc@10

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

1Brain & AI

0.8129

2Munich Logic Lab

0.7651

3Artem Blanar

0.7541

4linkP

0.7519

5dav0dea

0.7493

6Kim

0.7475

7MindLink

0.7430

8orionleeke

0.7430

9Brainmu Project

0.7411

10Hojun Yang

0.7395

11Varshith Madishetty

0.7372

12Jordan Griffith

0.7354

13yu_kuo14

0.7330

14Stéphane d'Ascoli

0.7309

15Jatin Arutla

0.7298

16Rohit Ravi

0.7293

17noah

0.7273

18NeuroMTEC

0.7181

19ottietjesesakfs

0.7180

20francescoilsazio

0.7175

Showing top 20 of 94 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	Brain & AI	0.8129	0.3966	1.2635	135
2	Munich Logic Lab	0.7651	0.2772	1.2085	103
3	Artem Blanar	0.7541	0.2577	1.1661	147
4	linkP	0.7519	0.3065	1.2133	105
5	dav0dea	0.7493	0.2959	1.2233	184
6	Kim	0.7475	0.2721	1.1469	164
7	MindLink	0.7430	0.2583	1.1625	308
8	orionleeke	0.7430	0.2380	1.1085	50
9	Brainmu Project	0.7411	0.3313	1.2020	51
10	Hojun Yang	0.7395	0.3481	1.1552	93
11	Varshith Madishetty	0.7372	0.3071	1.1479	140
12	Jordan Griffith	0.7354	0.3096	1.1960	242
13	yu_kuo14	0.7330	0.2630	1.1316	95
14	Stéphane d'Ascoli	0.7309	0.3062	1.1302	5
15	Jatin Arutla	0.7298	0.3048	1.1630	130
16	Rohit Ravi	0.7293	0.2748	1.0954	26
17	noah	0.7273	0.2479	1.0873	8
18	NeuroMTEC	0.7181	0.2613	1.1840	45
19	ottietjesesakfs	0.7180	0.2587	1.1591	348
20	francescoilsazio	0.7175	0.3400	1.1201	10
21	titus fisher	0.7173	0.2680	1.1617	110
22	snute220905	0.7171	0.3107	1.1544	13
23	InverseEncoder	0.7168	0.2565	1.1818	93
24	Umur Yıldız	0.7148	0.2432	1.1690	110
25	saharacamel	0.7143	0.2627	1.2085	151
26	Connor Finnerty	0.7062	0.2661	1.1639	107
27	BNEL	0.7028	0.2998	1.1866	57
28	Michal	0.7003	0.2814	1.1495	54
29	MagnetoLex	0.6989	0.2427	1.1564	68
30	cfw21w2	0.6984	0.2433	1.1607	74
31	Dimitar Terziev	0.6948	0.2681	1.0764	146
32	Valmik Nahata	0.6937	0.2199	1.0855	20
33	Picu	0.6915	0.2613	1.1359	38
34	Infera-Neuro	0.6876	0.2157	1.1848	75
35	ashley Iannetti	0.6824	0.2261	1.0698	96
36	MindReaders2.0	0.6821	0.2270	1.1921	252
37	Karahan Yılmazer	0.6809	0.2102	1.1583	87
38	peperonata	0.6791	0.2489	1.1776	38
39	Nobel Suhendra	0.6765	0.1996	1.1403	18
40	Viacheslav Fokin	0.6751	0.1839	1.1232	29
41	KLab	0.6638	0.2147	1.0454	7
42	Michael Ibrahim	0.6625	0.2277	1.1069	38
43	Nova	0.6620	0.2290	1.1888	17
44	CWBZ	0.6601	0.2089	1.1239	42
45	JovanaLab	0.6558	0.2729	1.0757	26
46	Yahya Abdulselam	0.6544	0.2340	1.1332	35
47	FengYuXiang 123	0.6528	0.2612	1.0857	41
48	kakuteki	0.6463	0.2239	1.1474	47
49	neural2speech	0.6447	0.1447	1.1265	10
50	Brain King	0.6441	0.1522	1.1299	71
51	@Arnauya	0.6428	0.1899	1.1423	81
52	langstudent	0.6328	0.2457	1.0446	24
53	albedoweb	0.6314	0.1481	0.9553	3
54	SENPAI	0.6296	0.1858	1.0606	61
55	MensaCard	0.6169	0.2029	1.1257	4
56	onlytry	0.6152	0.1934	1.0748	9
57	Ave_Dominus_Nox	0.5880	0.1761	1.0726	23
58	OmarDotEmam	0.5838	0.1797	1.0068	7
59	neuroclip	0.5707	0.0816	1.0056	1
60	syouya tobita	0.5658	0.1210	1.1454	18
61	Oysta A.H	0.5587	0.1156	1.0193	20
62	bcs	0.5418	0.0943	1.0338	19
63	Shuntaro Suzuki	0.5274	0.1625	1.0796	40
64	kongxuan47	0.4838	0.1019	0.9936	6
65	NJUersgogogo	0.4500	0.0716	0.9557	29
66	Baseline	0.4444	0.0733	0.9803	1
67	Sia	0.4362	0.1014	0.9362	5
68	Salsinats	0.4032	0.0693	0.8101	19
69	Abhijith Pradeep	0.3672	0.0641	0.8567	5
70	liuyishj	0.3343	0.0490	0.7152	9
71	Jun Jie Li	0.3176	0.0864	0.8436	12
72	monte-carlo	0.2900	0.0483	0.4671	11
73	George Yu	0.2878	0.0325	0.9547	4
74	Bhargav Kowshik	0.2871	0.0292	1.0947	16
75	BlueWire	0.2786	0.0467	0.8682	14
76	弗洛洛	0.2755	—	—	2
77	Fon1as	0.2538	0.0249	0.2581	1
78	willguido	0.2444	0.0548	0.6637	14
79	Devraj Rasal	0.2434	0.0118	1.0632	4
80	Akbar Permana	0.2422	0.0260	0.5392	2
81	immortal2	0.2407	0.0140	0.9038	1
82	Amal Messaoud	0.2374	0.0316	0.5402	9
83	Praise James	0.2230	0.0200	0.0248	3
84	Srinivas Calindi	0.2175	0.0373	0.2497	4
85	Nguyen Anh	0.2164	0.0311	0.5181	3
86	ML Learner26	0.2000	0.0200	0.0000	1
87	Akshat	0.2000	0.0200	0.0000	1
88	DongGua	0.2000	0.0200	0.0000	1
89	Athina Kanellatou	0.2000	0.0200	0.0000	1
90	Danka Khasanova	0.2000	0.0200	0.0000	1
91	Shriya Patkar	0.1950	0.0245	0.1998	1
92	lavender_lover	0.1906	0.0200	0.4893	3
93	LizaSheina	0.1880	0.0284	0.3681	1
94	Viknesh .V	0.1600	0.0200	0.0000	1
95	King	—	0.1601	1.0075	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 a separate holdout set and are confirmed through verification.

Updated … · Deep Track on Kaggle →