datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
mmlu-prox-eval-predictions
MMLU-ProX Multilingual Model Predictions
Raw per-sample model predictions on MMLU-ProX
across 29 languages and 25 open-weight LLMs, produced with
lm-evaluation-harness.
This dataset releases the full prediction logs (not just aggregate scores) so that
item-level responses can be re-analysed — e.g. for Item Response Theory (IRT) modelling
of multilingual benchmarks, error analysis, or per-item difficulty estimation.
Repository structure
mmlu_prox_<lang>/
└──… See the full description on the dataset page: https://huggingface.co/datasets/gililior/mmlu-prox-eval-predictions.polymarket-predictions
THE ORACLE — Polymarket predictions
Live predictions for Polymarket markets, produced by THE ORACLE — an autonomous
agent funded by $ORACLE pump.fun creator fees. Each row is a baseline-model
forecast over live orderbook signals (momentum, microstructure, liquidity).
predictions.json / predictions.csv — 100 markets, refreshed each agent cycle.
Columns: question, category, market_prob, oracle_prob, edge, confidence, signal,
model, backtest_acc, auc, modelability, volume… See the full description on the dataset page: https://huggingface.co/datasets/THEORACLEEEE/polymarket-predictions.dmi-aarhus-predictions
DMI Aarhus Predictions
Prediction and frontend contract dataset for the Aarhus weather pipeline. Maintained by Ciroc0.
Primary files
File
Purpose
Produced by
predictions_latest.parquet
Current future + verified prediction store
dmi-collector
frontend_snapshot.json
Primary integration contract for the Vercel frontend
dmi-collector
Compatibility files
File
Status
Notes
predictions.parquet
Legacy
Still read by compatibility… See the full description on the dataset page: https://huggingface.co/datasets/Ciroc0/dmi-aarhus-predictions.phantom-wiki-v0-5-0-predictions
Dataset Card for Dataset Name
Predictions from https://huggingface.co/datasets/mlcore/phantom-wiki-v050
Dataset Details
Dataset Description
Curated by: [More Information Needed]
Funded by [optional]: [More Information Needed]
Shared by [optional]: [More Information Needed]
Language(s) (NLP): [More Information Needed]
License: [More Information Needed]
Dataset Sources [optional]
Repository: [More Information Needed]
Paper [optional]: [More… See the full description on the dataset page: https://huggingface.co/datasets/kilian-group/phantom-wiki-v0-5-0-predictions.meowcat-predictions
MeowCat cell-type predictions on TCGA-LUAD and CPTAC-CCRCC
Per-pixel cell-type predictions generated by MeowCat on
H&E whole-slide images from two public cohorts:
Cohort
Tissue
Samples
h5ad payload
TCGA-LUAD
Lung adenocarcinoma
531
~60 GB
CPTAC-CCRCC
Clear-cell renal cell carcinoma
831
~93 GB
File layout
composition.parquet # long format: sample × cell_type → count, fraction
metadata.parquet # sample_id, cohort, patient_id, n_pixels… See the full description on the dataset page: https://huggingface.co/datasets/liranmao/meowcat-predictions.ord_predictions
Dataset Details
Dataset Description
The open reaction database is a database of chemical reactions and their conditions
Curated by:
License: CC BY SA 4.0
Dataset Sources
original data source
Citation
BibTeX:
@article{Kearnes_2021,
doi = {10.1021/jacs.1c09820},
url = {https://doi.org/10.1021%2Fjacs.1c09820},
year = 2021,
month = {nov},
publisher = {American Chemical Society ({ACS})},
volume = {143},
number = {45},
pages =… See the full description on the dataset page: https://huggingface.co/datasets/jablonkagroup/ord_predictions.ner-eval-predictionsPrediction-Smartphone-Addiction-Submission-V2Here's the enhanced version, honest summary of what actually moved the needle:
What improved it:
Feature engineering was the real driver: missingness indicators for every column (missingness itself carries signal here), plus ratio/interaction features like social_to_screen, sleep_deficit, weekday_weekend_diff, screen_per_age, etc.
LightGBM with these new features: OOF AUC 0.9628 (up from 0.9620).
Result:
submission_v2.csv, same valid format (296,302 rows… See the full description on the dataset page: https://huggingface.co/datasets/Qamro/Prediction-Smartphone-Addiction-Submission-V2.mpac-predictions
MPAC variant effect predictions
MPAC (Malinois with Parallel Aggregated Cross-validation) predicts cis-regulatory
activity of 200 bp human sequences in K562, HepG2 and SK-N-SH, and the allelic skew
caused by non-coding variants. This dataset holds the published predictions.
Identifying non-coding variant effects at scale via machine learning models of
cis-regulatory reporter assays.
The paper is the source of truth for how these tables were made and what they mean.
This is a… See the full description on the dataset page: https://huggingface.co/datasets/saarantras1/mpac-predictions.clinical-trial-outcomes-predictions
Clinical Trial Outcomes Prediction Dataset
A dataset of 1,366 binary forecasting questions about clinical trial outcomes, automatically generated and labeled using Lightning Rod Labs' Future-as-Label methodology.
Dataset Description
This dataset contains questions about pharmaceutical clinical trials from 2023-2024, paired with verified outcomes (success/failure). Each question asks whether a specific trial will meet its endpoints, receive FDA approval, or complete by a… See the full description on the dataset page: https://huggingface.co/datasets/3rdSon/clinical-trial-outcomes-predictions.negative-pi-predictions
negative-pi-predictions
what if π had digits before 3?
this dataset contains 100,000 digits predicted by a neural network at negative positions of π.
yes, this is exactly as stupid as it sounds.
what is this?
normally, we index the fractional digits of π like this:
position: 1 2 3 4 5 6 7 8 9 ...
digit: 1 4 1 5 9 2 6 5 3 ...
so:
π = 3.141592653589793...
↑
position 1
i trained a neural network to predict the digit at a given position using only… See the full description on the dataset page: https://huggingface.co/datasets/akaruineko/negative-pi-predictions.trace-rx-eval-predictions
TRACE-RX Evaluation Predictions
Per-image detector scores from an independent evaluation of the two TechJam 2026 TRACE-RX
detectors, run 30 Aug – 1 Sep 2026.
No images here. Every file contains scores, labels, asset ids and transform names only — this is
derived evaluation metadata, not a redistribution of any source imagery. The underlying corpora
(Joshyxwa/data_draft, Joshyxwa/techjam2026, techjam-aigc/wildfake-eval-subset) keep their own
terms, and data_draft's WildFake rows… See the full description on the dataset page: https://huggingface.co/datasets/joelleoqiyi/trace-rx-eval-predictions.gpu-forecasters-eval-set-predictionsCompanion artifact for GPU Forecasters: Language Models as Selective Surrogates for Kernel Runtime Optimization. Code: codezakh/gpu-surrogates.
Surrogate predictions on the held-out evaluation set. Each row is one forecast from one (surrogate, repeat) on one row of codezakh/gpu-forecasters-eval-set.
Loading
from datasets import load_dataset
# all surrogates and repeats
ds = load_dataset("codezakh/gpu-forecasters-eval-set-predictions", name="combined", split="predictions")
# one… See the full description on the dataset page: https://huggingface.co/datasets/codezakh/gpu-forecasters-eval-set-predictions.text-to-sql-eval-predictions
What the text-to-SQL models actually generated
Every prediction behind the numbers in
qwen3-8b-text2sql-qlora: the 453 test
questions of the enterprise text-to-SQL benchmark,
each answered by four configurations of the same model, each answer executed against the reference
PostgreSQL database and scored by comparing result sets. 1,812 rows.
I published this because the headline table (10.82 % → 50.99 % → 52.10 %) is the least interesting part of
that project. The interesting… See the full description on the dataset page: https://huggingface.co/datasets/hari-krishna-ai/text-to-sql-eval-predictions.bbnaija2026-predictionspatched_test_p_10_m1_predictions_v2
Dataset Card for "patched_test_p_10_m1_predictions_v2"
More Information needed
test-predictions-lyrics-titlePrediction-Smartphone-Addiction-Submission-in-Kaggle
📱 Prediction Smartphone Addiction - Competition Submission in Kaggle
This dataset contains the data and/or prediction results used for a Kaggle competition related to smartphone addiction prediction.
The project focuses on analyzing smartphone usage and related behavioral or demographic features to build machine learning models capable of predicting smartphone addiction levels.
🎯 Project Overview
Smartphone usage has become an important part of everyday life.… See the full description on the dataset page: https://huggingface.co/datasets/Qamro/Prediction-Smartphone-Addiction-Submission-in-Kaggle.patched_1000_test_p_150_m2_predictions
Dataset Card for "patched_1000_test_p_150_m2_predictions"
More Information needed
repro-ski-rental-with-distributional-predictions-of-unknown-quality-traces
Agent traces
Agent sessions published from a Trackio Logbook.
patched_1000_test_p_40_m2_predictions
Dataset Card for "patched_1000_test_p_40_m2_predictions"
More Information needed
patched_test_p_80_m1_predictions_v2
Dataset Card for "patched_test_p_80_m1_predictions_v2"
More Information needed
predictions_logistic_classifierABC-all-predictionsisafpressreleases_test_predictionsframes-benchmark-predictions
BENCH-04: N-8 Research Google FRAMES Benchmark Evaluation
Team Designation: N-8 ResearchLead Author: Greg VivianoOrganization: N-8 ResearchEvaluated Dataset: google/frames-benchmark (824 Questions)
Executive Summary
This repository contains the prediction dataset generated by N-8 Research's Deterministic Context Architecture across all 824 multi-step enterprise reasoning questions in Google's official google/frames-benchmark.
Performance Scorecard… See the full description on the dataset page: https://huggingface.co/datasets/gviviano/frames-benchmark-predictions.llm_predictionspredictions-dev-staging-project-vajra-dev-staging-l40-pcie-f0a7e41fspeccast-code-correctness-v1-2-blind-test-predictions
speccast-code-correctness-v1-2-blind-test-predictions
Blind test (n=975) predictions from final SpecCast v1.2 LoRA. Labels withheld.
Base model: Qwen/Qwen3.5-4B
Adapter: LightningRodLabs/speccast-code-correctness-v1-2-qwen3.5-4b-lora
Source benchmark: aligncast/speccast-benchmark @ 7cef3c2…
Rows: 975
Upstream artifact: LightningRodLabs/speccast-code-correctness-v1-2-blind-test-qwen3-5-4b-blind-test-ckpt-20260722T123227Z
Blind splits keep labels empty by design.
patched_test_p_40_m1_predictions_v3
Dataset Card for "patched_test_p_40_m1_predictions_v3"
More Information needed