Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Conformal Prediction research benchmarks – Page 8 · SOTA2 Research

Conformal Prediction

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

1.685Average Length

4

Feb 26, 2026

facebook 2 (test)

1.075Average Length

4

Feb 26, 2026

facebook 1 (test)

1.072Average Length

4

Feb 26, 2026

QualityMRI (test)

0.33Conditional Saturation

3

Jul 9, 2026

ChaosNLI (test)

Calibrated BPS with first-order

91Conditional Saturation

3

Jul 9, 2026

wind direction dataset (test)

Projected random forests

1.9Median

3

Jun 11, 2026

CIFAR-10 2009 (test)

89.9Marginal Coverage

3

Mar 17, 2026

Synthetic dataset Calib ID vs Test Shift (test)

95.22Coverage (%)

3

Feb 26, 2026

Synthetic dataset Calib ID vs Test ID (test)

95.11Coverage

3

Feb 26, 2026

Tox21 Y=1 (Scaffold Splitting)

Unweighted (baseline)

93Coverage

3

Feb 26, 2026

Tox21 Y=0 (Scaffold Splitting)

CoDrug (Energy)

91Coverage

3

Feb 26, 2026

HIV (Y=1) (Scaffold Splitting)

CoDrug (Energy)

90Coverage

3

Feb 26, 2026

HIV Y=0 (Scaffold Splitting)

Unweighted (baseline)

91Coverage

3

Feb 26, 2026

ClinTox Y=1 (Scaffold Splitting)

Unweighted (baseline)

97Coverage

3

Feb 26, 2026

ClinTox Y=0 (Scaffold Splitting)

CoDrug (Energy)

90Coverage

3

Feb 26, 2026

AMES Y=1 (Scaffold Splitting)

Unweighted (baseline)

85Coverage

3

Feb 26, 2026

AMES Y=0 (Scaffold Splitting)

CoDrug (Feature)

89Coverage

3

Feb 26, 2026

Tox21 Y=1 (Fingerprint Splitting)

CoDrug (Energy)

0.97Coverage

3

Feb 26, 2026

Tox21 (Y=0) (Fingerprint Splitting)

CoDrug (Energy)

0.9Coverage

3

Feb 26, 2026

HIV Y=1 Fingerprint Splitting

CoDrug (Feature)

95Coverage

3

Feb 26, 2026

HIV Y=0 (Fingerprint Splitting)

Unweighted (baseline)

93Coverage

3

Feb 26, 2026

ClinTox Y=1 (Fingerprint Splitting)

Unweighted (baseline)

80Coverage

3

Feb 26, 2026

ClinTox (Y=0) (Fingerprint Splitting)

CoDrug (Energy)

86Coverage

3

Feb 26, 2026

AMES Y=1 (Fingerprint Splitting)

CoDrug (Feature)

90Coverage

3

Feb 26, 2026

AMES Y=0 (Fingerprint Splitting)

Unweighted (baseline)

100Coverage

3

Feb 26, 2026

Page 8 of 9

Popular datasets

Synthetic Data CIFAR ImageNet Long-form QA Synthetic

Follow for updates

Join SOTA2 Contact