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 Consistency Evaluation research benchmarks · SOTA2 Research

Human Consistency Evaluation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

38.4Kendall's Tau-c

16

May 22, 2026

33.9Kendall's Tau

11

Apr 30, 2026

MLLM-as-a-Judge

30.3CO Consistency Score

11

Apr 30, 2026

Q-Reasoning (test)

Proposed Human-Like Reasoning Framework (detailed)

51.4ROUGE-1 Score

6

Feb 26, 2026

Popular datasets

GenAI-Bench RichHF MLLM-as-a-Judge Q-Reasoning

Follow for updates

Join SOTA2 Contact