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

Controllability research benchmarks · SOTA2 Research

Controllability

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

90.38Controllability Score

40

Feb 26, 2026

100PolyGuard

40

Feb 26, 2026

87.5HarmBench Score

40

Feb 26, 2026

HDPCG Space Scale L (aggregated runs)

1.343MAE (Density)

3

Feb 26, 2026

HDPCG Space Scale M (aggregated runs)

1.366MAE (Density)

3

Feb 26, 2026

HDPCG Space Scale S (aggregated runs)

2.217MAE (Density)

3

Feb 26, 2026

Harmless-helpful Group 4 (unseen)

1Kendall's Tau

2

Apr 7, 2026

Harmless-helpful Group 3 (unseen)

1Kendall's Tau

2

Apr 7, 2026

Harmless-helpful Group 2 (unseen)

1Kendall's tau

2

Apr 7, 2026

Harmless-helpful Group 1 (unseen)

1Kendall's Tau

2

Apr 7, 2026

Humor-helpful Group 4 (unseen)

1Kendall's tau

2

Apr 7, 2026

Humor-helpful Group 3 (unseen)

1Kendall's tau

2

Apr 7, 2026

Humor-helpful Group 2 (unseen)

1Kendall's Tau

2

Apr 7, 2026

Humor-helpful Group 1 (unseen)

1Kendall's Tau

2

Apr 7, 2026

Popular datasets

Humor-helpful Harmless-helpful HDPCG Space HarmBench Polyguard

Follow for updates

Join SOTA2 Contact