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

Feedback Evaluation Alignment research benchmarks · SOTA2 Research

Feedback Evaluation Alignment

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

0.494Kendall's Tau

11

Feb 26, 2026

0.423Kendall's Tau

6

Feb 26, 2026

Prometheus-2-7B

0.405Kendall's Tau

6

Feb 26, 2026

Mistral-7B-Instruct + CE (GPT-4 Score)

82.4Kendall's Tau

6

Feb 26, 2026

Popular datasets

MT-Bench Feedback Bench FLASK Vicuna Bench

Follow for updates

Join SOTA2 Contact