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

Human alignment evaluation research benchmarks · SOTA2 Research

Human alignment evaluation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

LaMP Citation Identification, Movie Tagging, and Product Rating (test)

100Pos Score

56

Jun 16, 2026

Vicuna Evaluation Benchmark

76.3Accuracy

16

Feb 26, 2026

0.367Pearson Correlation (Mean)

14

Apr 7, 2026

Human Judgment Dataset

0.166Coherence RMSE

3

Feb 26, 2026

StarCraft II Human Alignment Evaluation (test)

5Expert Bug Exploitation Score

2

May 6, 2026

Generated Content Evaluation Dataset

32Coherence

2

Feb 26, 2026

Popular datasets

Vicuna LaMP Generated Content Evaluation Dataset Human Judgment GenOverall

Follow for updates

Join SOTA2 Contact