v5.3 Dataset — the Numerai Tournament

"Quantum" released in July 2026. This dataset introduces 807 new features. The default target is Ender-60: target aliases target_ender_60, while target_ender_20 remains available explicitly. All files are only in int8 formats.

train.parquet

Data used to train your model

validation.parquet

Data used to validate or train your model. This expands every week. Recent eras can have null target_ender_60 (and null target alias) until their 60-day returns mature; filter on the explicit target you use.

validation_example_preds.parquet

Ender-60 example predictions from the v53_lgbm_ender60 model on validation.parquet, for eras with a mature target.

live.parquet

The live data that your model predicts on. This changes daily.

live_example_preds.parquet

Ender-60 example predictions from the v53_lgbm_ender60 model on the live.parquet file. Allows you to easily try your first submission.

features.json

JSON file with statistics about each feature in the dataset and some pre-made feature sets to make modeling easier.

train_benchmark_models.parquet

A file with benchmark model predictions for some of the train data.

validation_benchmark_models.parquet

A file with all benchmark model predictions for validation data.

live_benchmark_models.parquet

A file with all benchmark model predictions for live data.

meta_model.parquet

The Meta Model gives you insights on how your model would have altered the Meta Model historically, as well as how closely your predictions align with or diverge from the consensus signal, helping you optimize for metrics like MMC. This version of the Meta Model is only available from era 1133 onwards.