Foundation model

BrainOmni: results on public EEG datasets

BrainOmni is a pretrained foundation model for EEG and MEG, released in tiny and base sizes, with a BrainTokenizer front end; its paper's appendix lists the EEG and MEG recordings it was pretrained on. BCI Report ran Base frozen on six of the eight core protocols: its tokenizer needs two-second windows, so the two one-second ERP protocols were not run. It keeps its upstream common average reference on the small layouts here.

Measured on: ds003810; EEGMAT; BETA; EESM19 scalp subset; ds005342 · Protocols: Motor imagery & rest; Arithmetic & rest; SSVEP · 8 channels; SSVEP · 4 channels; Sleep staging; Idle & command

Also known as BrainOmni Base · BrainTokenizer · OpenTSLab/BrainOmni

Reference BrainOmni, arXiv:2505.18185 ↗

Directory status: Evaluated (6 of 8 protocols) · Description sources arxiv.org

Published results

Compare figures within a group only: task, cohort, chance level and electrode layout can differ between groups. One row is above another only where their 95% intervals do not overlap.

ds003810 · Further foundation encoders, frozen · motor imagery & rest

Source page: Core-matrix protocol: Motor imagery & rest · Chance level 50.0% · foundation-models-mi-rest.csv

MethodConditionMetricValuePeople
BrainOmni BaseFrozen encoder + ridge headBalanced accuracy58.8%57.0%–60.8%10

Weights terms: BrainOmni under MIT. Every weights licence and its terms →

EEGMAT · Further foundation encoders, frozen · arithmetic & rest

Source page: Core-matrix protocol: Arithmetic & rest · Chance level 50.0% · foundation-models-arithmetic-rest.csv

MethodConditionMetricValuePeople
BrainOmni BaseFrozen encoder + ridge headBalanced accuracy61.6%58.4%–64.9%36

Weights terms: BrainOmni under MIT. Every weights licence and its terms →

EEGMAT · Model adaptation, further encoders · new people, same task, one fixed recipe

Source page: Core-matrix protocol: Arithmetic & rest · Chance level 50.0% · foundation-models-update.json

BrainOmni Base · Frozen encoder + trained head
64.5% (59.6%–69.2%)
BrainOmni Base · LoRA rank 4 + head
64.8% (59.6%–69.7%)
Balanced accuracy, 2 configurations. Dot: the estimate; line: 95% interval; dashed line, where drawn: chance level.
MethodConditionMetricValuePeople
BrainOmni BaseFrozen encoder + trained headBalanced accuracy64.5%59.6%–69.2%16,386 trainable parameters.36
BrainOmni BaseLoRA rank 4 + headBalanced accuracy64.8%59.6%–69.7%106,498 trainable parameters.36
BrainOmni BaseLoRA minus frozen + head, same people and foldsPaired difference+0.3 pp−1.4 pp–+1.8 pp18 people improved, 14 got worse, 4 unchanged. The interval includes zero: no change is established.36

Weights terms: BrainOmni under MIT. Every weights licence and its terms →

BETA · Further foundation encoders, frozen · SSVEP, 8 channels

Source page: Core-matrix protocol: SSVEP · 8 channels · Chance level 2.5% · foundation-models-beta-8ch.csv

MethodConditionMetricValuePeople
BrainOmni BaseFrozen encoder + ridge headBalanced accuracy21.7%18.6%–25.0%70

Weights terms: BrainOmni under MIT. Every weights licence and its terms →

BETA · Further foundation encoders, frozen · SSVEP, 4 channels

Source page: Core-matrix protocol: SSVEP · 4 channels · Chance level 2.5% · foundation-models-beta-4ch.csv

MethodConditionMetricValuePeople
BrainOmni BaseFrozen encoder + ridge headBalanced accuracy13.0%10.6%–15.6%70

Weights terms: BrainOmni under MIT. Every weights licence and its terms →

ds006593 · Further foundation encoders, frozen · P300 target ERP

Source page: Core-matrix protocol: P300 target ERP · Chance level 50.0% ·

BrainOmni Base: not run. BrainTokenizer needs a 512-sample window (2.0 s at 256 Hz); the published segment is 1 s = 256 samples, so upstream unfold() would zero-pad 256 of 512 samples of every window (invented samples). All upstream downstream tasks use >= 2 s windows.

TMNRED / ds005383 · Further foundation encoders, frozen · semantic target ERP

Source page: Core-matrix protocol: Semantic target ERP · Chance level 50.0% ·

BrainOmni Base: not run. BrainTokenizer needs a 512-sample window (2.0 s at 256 Hz); the published segment is 1 s = 256 samples, so upstream unfold() would zero-pad 256 of 512 samples of every window (invented samples). All upstream downstream tasks use >= 2 s windows.

EESM19 scalp subset · Further foundation encoders, frozen · sleep staging

Source page: Core-matrix protocol: Sleep staging · Chance level 20.0% · foundation-models-sleep-scalp.csv

MethodConditionMetricValuePeople
BrainOmni BaseFrozen encoder + ridge headBalanced accuracy67.7%65.8%–69.5%20

Weights terms: BrainOmni under MIT. Every weights licence and its terms →

ds005342 · Further foundation encoders, frozen · idle & command

Source page: Core-matrix protocol: Idle & command · foundation-models-idle.csv

MethodConditionMetricValuePeople
BrainOmni BaseFrozen encoder + linear headCommands detected ≤3 s13 / 601 of 4 people always abstained.4
BrainOmni BaseFrozen encoder + linear headIdle false activations3 / 604

Weights terms: BrainOmni under MIT. Every weights licence and its terms →

All methods → · All datasets →

Checkpoints, inputs and terms

No model’s authors endorse these results. No weights, adapted weights or LoRA deltas were kept or shared.

BrainOmni Base

Panel
A row beside the core matrix on every protocol page
Encoder parameters
31.84M
Revision
OpenTSLab/BrainOmni @ 9a4d3c70
Checkpoint SHA-256
435db24e57a55df05aa7e16355def7b7ecbedb22aa1ec16063e7d14efd2386d0
Weights licence
MIT
Rights review
Permissive weights licence; aggregate scores only, no weights redistributed.
Row footnote
p300-target and semantic-target not run: the 2 s tokenizer window cannot be met by 1 s segments without zero padding. Upstream common average reference kept on 4-8 channel montages.
EEGMAT adaptation
Run: a head trained on the frozen encoder against LoRA rank 4, three seeds.

Pretraining exposure, by dataset

Whether each core dataset is in the model authors’ published pretraining list, checked on 2026-10-04 at dataset level and linked to the source; a dataset absent from the list may still overlap the pretraining data.

DatasetProtocolsStatementSource
ds003810 Motor Imagery vs Rest (low-cost EEG; Peterson et al.)Motor imagery & restnot in the authors' published pretraining list (checked 2026-10-04)source ↗
EEGMAT (PhysioNet EEG During Mental Arithmetic Tasks; Zyma et al. 2019)Arithmetic & restnot in the authors' published pretraining list (checked 2026-10-04)source ↗
ds006593 cBCI Matrix Multimodal Dataset (Celik et al.)P300 target ERPnot in the authors' published pretraining list (checked 2026-10-04)source ↗
ds005383 TMNRED (Bai et al. 2025, Sci. Data 12:701)Semantic target ERPnot in the authors' published pretraining list (checked 2026-10-04)source ↗
EESM19 Ear-EEG Sleep Monitoring 2019 (OpenNeuro ds005185; Mikkelsen et al.)Sleep stagingnot in the authors' published pretraining list (checked 2026-10-04)source ↗
BETA 40-target SSVEP (Liu et al. 2020, Front. Neurosci. 14:627)SSVEP · 8 channels · SSVEP · 4 channelsnot in the authors' published pretraining list (checked 2026-10-04)source ↗
ds005342 EEG offline/online MI for standing and sitting (Triana-Guzman et al.)Idle & commandnot in the authors' published pretraining list (checked 2026-10-04)source ↗

Cite this page

BCI Report (2026). BrainOmni: results on public EEG datasets. https://bci.report/methods/brainomni/

Figures from release foundation-models-update-20261004 (2026-10-04). Cite the upstream datasets as well: each dataset’s page gives its credit.

Every release is archived on Zenodo: doi:10.5281/zenodo.23123296. BibTeX for the site and its releases → · CITATION.cff ↗